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

    Neuronpedia

    INDEX
    Explanations

    instances where permission or allowance is granted

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to permission or granting access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.84
    borough
    -0.77
    ãĤ©
    -0.76
    bard
    -0.71
    punk
    -0.71
    schild
    -0.70
    bons
    -0.69
    marine
    -0.69
    figure
    -0.68
    cal
    -0.68
    POSITIVE LOGITS
     us
    0.96
     unrestricted
    0.95
     exceptions
    0.95
     outsiders
    0.91
     them
    0.88
     him
    0.83
     foreigners
    0.82
     rapists
    0.82
     unlimited
    0.81
     exemptions
    0.81
    Act Density 0.079%

    No Known Activations