© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 894
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of inadequacy or insufficiency

    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
    terness
    -0.77
    itars
    -0.77
    bats
    -0.76
    poons
    -0.73
    ouls
    -0.73
    iffs
    -0.69
    bons
    -0.67
    intent
    -0.66
     farmland
    -0.66
    mans
    -0.65
    POSITIVE LOGITS
     two
    0.69
     few
    0.68
    agus
    0.67
     several
    0.67
     many
    0.65
     three
    0.64
    recated
    0.63
    stood
    0.62
    TY
    0.62
    ּ
    0.62
    Activations Density 0.068%

    No Known Activations