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

    Neuronpedia

    INDEX
    Explanations

    assertive affirmations or strong agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.74
     Stevenson
    -0.74
    mujeres
    -0.72
     Baumann
    -0.69
    gäng
    -0.68
    SourceChecksum
    -0.67
     emotions
    -0.66
    ../../
    -0.64
     Bischof
    -0.64
     Malone
    -0.64
    POSITIVE LOGITS
     certainly
    0.95
     Certainly
    0.93
    certainly
    0.92
    Certainly
    0.88
     surely
    0.69
     ciertamente
    0.67
    tableFuture
    0.66
    Steuer
    0.66
     Surely
    0.66
     sicherlich
    0.64
    Act Density 0.055%

    No Known Activations