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

    Neuronpedia

    INDEX
    Explanations

    numerical values within a range

    oai_token-act-pair · gpt-3.5-turbo

    references to voting or poll results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.88
     tradem
    -0.81
     srf
    -0.75
    ierrez
    -0.74
    spread
    -0.71
    ifully
    -0.70
    anamo
    -0.69
     consolid
    -0.67
    ¥ŀ
    -0.66
    gart
    -0.65
    POSITIVE LOGITS
    66
    1.05
    37
    0.98
    rd
    0.98
    87
    0.93
    94
    0.92
    97
    0.92
    33
    0.91
    77
    0.90
    76
    0.90
    63
    0.89
    Act Density 0.025%

    No Known Activations