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

    Neuronpedia

    INDEX
    Explanations

    references to television programs and websites

    oai_token-act-pair · gpt-3.5-turbo

    references to television and streaming platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.83
    REDACTED
    -0.68
     Parish
    -0.63
     Hawth
    -0.62
    cies
    -0.62
    drawn
    -0.61
     Carly
    -0.60
    士
    -0.60
    imentary
    -0.60
    cedes
    -0.58
    POSITIVE LOGITS
    ographers
    0.90
    itsu
    0.89
    oday
    0.86
    rx
    0.85
    ideo
    0.83
    ovies
    0.82
    ograp
    0.80
    orsi
    0.79
    urnal
    0.78
    ::::
    0.78
    Act Density 0.022%

    No Known Activations