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

    Neuronpedia

    INDEX
    Explanations

    details related to movies and cultural references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gencies
    -0.91
    teness
    -0.86
    acity
    -0.82
    fw
    -0.80
    apo
    -0.79
    alde
    -0.78
    ffect
    -0.77
    erity
    -0.74
    parency
    -0.72
    arers
    -0.72
    POSITIVE LOGITS
     classic
    0.87
     bestselling
    0.86
     copyrighted
    0.84
     Akira
    0.80
     Herman
    0.79
     Gothic
    0.79
     classics
    0.77
     medieval
    0.76
     popular
    0.75
     screenplay
    0.75
    Act Density 0.135%

    No Known Activations