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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions in computer code

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to incidents or events involving legal or criminal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itaire
    -0.62
    ãĥĩãĤ£
    -0.58
    tyard
    -0.57
    =]
    -0.55
    viation
    -0.54
    emale
    -0.52
    arton
    -0.52
    pecting
    -0.52
    thouse
    -0.51
    untarily
    -0.50
    POSITIVE LOGITS
    ¶
    0.67
    RESULTS
    0.63
     Finally
    0.60
    Finally
    0.60
     Else
    0.60
     Morsi
    0.59
     GOODMAN
    0.58
    CVE
    0.57
     Canaver
    0.57
    Still
    0.55
    Act Density 1.317%

    No Known Activations