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

    Neuronpedia

    INDEX
    Explanations

    Instances of emphasis or exaggeration in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.79
    inarily
    -0.71
    ords
    -0.69
    issance
    -0.69
    riots
    -0.68
    craft
    -0.68
    enance
    -0.63
    isode
    -0.63
    iens
    -0.62
    legram
    -0.62
    POSITIVE LOGITS
     far
    0.83
     much
    0.82
     busy
    0.82
     distracting
    0.81
     risky
    0.81
     tempting
    0.80
     simplistic
    0.80
     afraid
    0.78
     costly
    0.75
     cozy
    0.74
    Act Density 0.042%

    No Known Activations