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

    Neuronpedia

    INDEX
    Explanations

    questions and exclamatory statements that express disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammans
    -0.61
     pinulongan
    -0.60
    SharedCtor
    -0.57
     surla
    -0.57
    WireFormatLite
    -0.56
     ProtoMessage
    -0.56
    hyrchwyd
    -0.56
    migrationBuilder
    -0.51
    UnusedPrivate
    -0.49
    ThroughAttribute
    -0.48
    POSITIVE LOGITS
     why
    1.02
    why
    0.88
     Why
    0.85
    Why
    0.85
     nobody
    0.79
    Maybe
    0.73
     pourquoi
    0.72
     warum
    0.71
     varför
    0.71
     maybe
    0.69
    Act Density 1.006%

    No Known Activations