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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and titles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereto
    -0.65
    İĭ
    -0.62
     thereof
    -0.61
     precursor
    -0.57
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.55
    ãĤ¼ãĤ¦ãĤ¹
    -0.55
    âĸ¬
    -0.54
     respectively
    -0.53
    EStream
    -0.53
    ĵĺ
    -0.53
    POSITIVE LOGITS
    resa
    0.80
    xiety
    0.77
    ifax
    0.75
    hesda
    0.73
    oton
    0.72
    icester
    0.71
    cohol
    0.69
    asionally
    0.69
    ston
    0.69
    erm
    0.69
    Act Density 0.373%

    No Known Activations