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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures encouraging action or behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to gameplay or gaming mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    burn
    -0.85
    minist
    -0.79
    geries
    -0.72
    boro
    -0.71
    dos
    -0.64
    lections
    -0.62
    heit
    -0.62
    rad
    -0.61
     footing
    -0.60
    cape
    -0.60
    POSITIVE LOGITS
    Additionally
    0.83
    Furthermore
    0.83
    Nevertheless
    0.78
    Nonetheless
    0.78
    However
    0.77
    ³³³³
    0.76
    Moreover
    0.76
    ³³³³³³³³³³³³³³³³
    0.74
    PHOTOS
    0.73
    Interestingly
    0.73
    Act Density 0.465%

    No Known Activations