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

    Neuronpedia

    INDEX
    Explanations

    mention of sci-fi related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to science fiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.95
    theless
    -0.94
    xual
    -0.80
     LIA
    -0.78
    holders
    -0.77
    esville
    -0.73
     bearer
    -0.69
    upon
    -0.69
     dismissing
    -0.68
    holder
    -0.68
    POSITIVE LOGITS
     sci
    0.92
     fiction
    0.83
    adelphia
    0.80
    posium
    0.78
     fi
    0.77
    pt
    0.75
    uristic
    0.75
    Fi
    0.70
    oto
    0.70
    osc
    0.70
    Act Density 0.022%

    No Known Activations