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

    Neuronpedia

    INDEX
    Explanations

    information related to numerical quantities and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perspect
    -0.78
     advoc
    -0.74
     enthusi
    -0.71
     princ
    -0.69
     nodd
    -0.67
     philos
    -0.67
     duty
    -0.66
     conduc
    -0.66
     privileges
    -0.66
     corrections
    -0.65
    POSITIVE LOGITS
    5
    1.94
    6
    1.80
    8
    1.79
    7
    1.78
    4
    1.77
    3
    1.76
    9
    1.70
    2
    1.66
    1
    1.58
    75
    1.58
    Act Density 0.059%

    No Known Activations