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

    Neuronpedia

    INDEX
    Explanations

    texts related to voting and results, with some mentions of travel and jobs

    oai_token-act-pair · gpt-3.5-turbo

    references to personal actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.84
    sequently
    -0.77
     advoc
    -0.65
    Due
    -0.64
    shown
    -0.63
    Additionally
    -0.62
    ividual
    -0.62
    Furthermore
    -0.61
    similar
    -0.61
    Similarly
    -0.60
    POSITIVE LOGITS
     ain
    0.82
     damned
    0.79
    !)
    0.72
     roar
    0.71
     ya
    0.70
    )!
    0.70
     huh
    0.70
    ?!
    0.70
     damn
    0.70
     kidding
    0.69
    Act Density 1.076%

    No Known Activations