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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific notable individuals or character names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exch
    -0.75
    unicip
    -0.74
     facilit
    -0.70
    quartered
    -0.70
     moderation
    -0.68
     preventive
    -0.68
    tml
    -0.67
    iminary
    -0.67
    ledged
    -0.67
    iliated
    -0.67
    POSITIVE LOGITS
     Dracula
    1.06
     Cage
    1.02
     Kubrick
    0.96
     trilogy
    0.94
     Goes
    0.93
     Gunn
    0.89
     Reeves
    0.89
     Trilogy
    0.89
     Frankenstein
    0.89
     Bones
    0.88
    Act Density 0.320%

    No Known Activations