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

    Neuronpedia

    INDEX
    Explanations

    references to statistical figures and trends

    oai_token-act-pair · gpt-3.5-turbo

    statistical information and data about societal trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ':
    -0.67
    isations
    -0.66
    pac
    -0.65
    ãĥij
    -0.61
    cos
    -0.59
    atre
    -0.59
    angs
    -0.59
    ::::::::
    -0.58
    ãĥ¤
    -0.58
    colour
    -0.58
    POSITIVE LOGITS
     moreover
    0.80
     scarcely
    0.79
     doubtless
    0.79
     hardly
    0.78
     presumably
    0.76
     surely
    0.71
     virtually
    0.70
     attest
    0.70
     triv
    0.70
     barely
    0.69
    Act Density 1.104%

    No Known Activations