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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    prominent names or titles associated with notable individuals or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOS
    -0.77
     wise
    -0.76
    pmwiki
    -0.72
    irmed
    -0.65
    ierra
    -0.65
    ibaba
    -0.62
     silenced
    -0.61
    gamer
    -0.60
     condem
    -0.59
    >[
    -0.59
    POSITIVE LOGITS
    sonian
    0.88
    stown
    0.88
     Horton
    0.78
    sburg
    0.75
     Awards
    0.74
    bourg
    0.73
     River
    0.72
     Canyon
    0.71
    ween
    0.71
     Brothers
    0.70
    Act Density 0.314%

    No Known Activations