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

    Neuronpedia

    INDEX
    Explanations

    French words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific words or phrases with potential variations in spelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vasive
    -0.78
    phones
    -0.74
    tree
    -0.72
    crow
    -0.69
    ffer
    -0.69
    stocks
    -0.69
    ften
    -0.66
    cox
    -0.65
    jri
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    POSITIVE LOGITS
    iquette
    1.02
    ica
    0.93
    ablish
    0.90
    roit
    0.88
    itle
    0.84
    ablishment
    0.82
    ieth
    0.82
    ablished
    0.81
    ico
    0.80
    EXT
    0.80
    Act Density 0.012%

    No Known Activations