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

    Neuronpedia

    INDEX
    Explanations

    references to photographs within sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to photos or images in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osi
    -0.73
     congress
    -0.66
    OWER
    -0.61
     theorem
    -0.59
     allele
    -0.57
     bloc
    -0.57
     defe
    -0.57
     nonviolent
    -0.57
     streng
    -0.57
     Stra
    -0.57
    POSITIVE LOGITS
    ynthesis
    1.47
    ensitive
    1.23
    ynt
    1.20
    mith
    1.09
     depicting
    1.00
    hops
    0.96
    poons
    0.95
    paces
    0.95
    heet
    0.94
    creen
    0.94
    Act Density 0.053%

    No Known Activations