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

    Neuronpedia

    INDEX
    Explanations

    quotes and discussions related to movie production and casting decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     increa
    -2.50
     indestru
    -2.38
     swarovski
    -2.38
     squa
    -2.36
     encomp
    -2.31
     affor
    -2.29
     madonna
    -2.29
     suscep
    -2.27
     unwarran
    -2.26
     hairc
    -2.26
    POSITIVE LOGITS
     definitely
    0.82
    <bos>
    0.79
     certainly
    0.78
     [
    0.77
     plans
    0.77
     plan
    0.75
    ”
    0.75
     will
    0.75
     very
    0.75
    ́
    0.74
    Act Density 0.353%

    No Known Activations