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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to connection or association

    oai_token-act-pair · gpt-3.5-turbo

    terms related to connections and associations between concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bis
    -0.74
    itol
    -0.73
    achment
    -0.71
    rit
    -0.71
    by
    -0.69
    vertising
    -0.68
    sie
    -0.67
    mpeg
    -0.67
    oÄŁ
    -0.67
    =-=-=-=-
    -0.66
    POSITIVE LOGITS
     dots
    1.26
     disparate
    1.05
     apples
    0.99
     together
    0.91
     them
    0.86
     themselves
    0.76
     sexes
    0.76
     oneself
    0.75
     favorably
    0.73
     seamlessly
    0.72
    Act Density 0.134%

    No Known Activations