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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 155
    Prev
    Next
    INDEX
    Explanations

    the repeated phrase "Even" indicative of contrast or contradiction

    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
    vironment
    -0.85
    ノ
    -0.83
    Shape
    -0.82
    ゴン
    -0.75
    ヘラ
    -0.74
    obs
    -0.74
    psc
    -0.73
    cipl
    -0.73
    Unknown
    -0.72
    qi
    -0.72
    POSITIVE LOGITS
     Gavin
    0.67
     BET
    0.66
     Adobe
    0.65
     CLS
    0.65
     Guatem
    0.64
     CC
    0.64
     ICE
    0.64
     Clement
    0.64
     Cummings
    0.63
     Hond
    0.63
    Activations Density 0.040%

    No Known Activations