Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 384
    Prev
    Next
    INDEX
    Explanations

    expressions of advocacy and support for rights and social causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vertisement
    -0.79
     Klux
    -0.77
    ratch
    -0.77
    ivated
    -0.76
    ivid
    -0.75
     dstg
    -0.73
    76561
    -0.72
    igslist
    -0.71
    behind
    -0.71
    pose
    -0.70
    POSITIVE LOGITS
     dignity
    0.96
     excellence
    0.82
     decency
    0.77
     lifes
    0.74
     fairness
    0.74
     goodness
    0.73
     ending
    0.72
     equal
    0.70
     morality
    0.70
     diversity
    0.69
    Activations Density 0.124%

    No Known Activations