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

    Neuronpedia

    INDEX
    Explanations

    actions related to societal participation or contribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions and contributions of individuals within a community or society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %.
    -0.68
    iven
    -0.64
    among
    -0.63
    UNCH
    -0.61
    asking
    -0.61
    actly
    -0.60
    %;
    -0.58
    ';
    -0.57
     ',
    -0.57
    `.
    -0.57
    POSITIVE LOGITS
     aren
    0.90
     weren
    0.85
     are
    0.82
     were
    0.77
    pires
    0.74
     cannot
    0.72
     contrace
    0.69
     shouldn
    0.69
     benefited
    0.68
     differed
    0.64
    Act Density 0.403%

    No Known Activations