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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions towards a specific goal

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and references to financial or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.72
    bara
    -0.62
    ÙĬ
    -0.61
    ãĥ¯
    -0.59
    ÙĦ
    -0.58
    ''''
    -0.57
    ecause
    -0.57
    ب
    -0.57
    olean
    -0.57
    Synopsis
    -0.56
    POSITIVE LOGITS
    EStream
    1.02
    ĸļ
    0.88
     Gutenberg
    0.77
    kefeller
    0.75
    ibaba
    0.73
    rences
    0.72
    ß
    0.70
     Bucs
    0.68
     tradem
    0.66
    pty
    0.66
    Act Density 7.265%

    No Known Activations