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. 386
    Prev
    Next
    INDEX
    Explanations

    phrases indicating separation or distance from something

    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
    tto
    -0.76
    ople
    -0.74
    TABLE
    -0.66
    rie
    -0.65
    rose
    -0.63
    zer
    -0.63
    isse
    -0.63
    bid
    -0.62
    ises
    -0.61
    ki
    -0.60
    POSITIVE LOGITS
    �
    0.62
     Revision
    0.61
     Struggle
    0.59
    ��
    0.59
     Peer
    0.58
    ��
    0.54
     civilized
    0.54
     endured
    0.54
    ��
    0.53
    ress
    0.52
    Activations Density 0.134%

    No Known Activations