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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and specific formatting symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ela
    -0.86
    elo
    -0.79
    ãĥ¯
    -0.78
    Tes
    -0.77
    TPS
    -0.74
    ba
    -0.72
     Tes
    -0.71
     Alic
    -0.71
    ula
    -0.70
     Kelvin
    -0.70
    POSITIVE LOGITS
    11
    1.31
     11
    1.21
     111
    1.01
    111
    0.94
     117
    0.94
    112
    0.94
    Rah
    0.93
    November
    0.90
     116
    0.89
    1200
    0.88
    Act Density 0.141%

    No Known Activations