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

    Neuronpedia

    INDEX
    Explanations

    references to global or worldwide contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to global or worldwide contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -1.09
    »Ĵ
    -0.95
    ippi
    -0.91
    odox
    -0.83
    utenant
    -0.83
    iple
    -0.82
    abee
    -0.81
    Ô
    -0.78
    sbm
    -0.78
     Mn
    -0.72
    POSITIVE LOGITS
     premiere
    0.77
     warming
    0.73
     Bahá
    0.73
     treaty
    0.73
     renowned
    0.71
     economy
    0.70
    locked
    0.69
    Tour
    0.69
    cup
    0.69
     except
    0.69
    Act Density 0.064%

    No Known Activations