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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal stories or experiences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and transitional phrases that indicate continuity in speech or writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ãį
    -0.68
     slate
    -0.63
    retty
    -0.63
    estyles
    -0.62
     rall
    -0.60
     hell
    -0.59
     mas
    -0.58
    ã
    -0.58
    ño
    -0.58
     cas
    -0.57
    POSITIVE LOGITS
    printf
    0.64
    attery
    0.63
    men
    0.60
     Gou
    0.59
    kick
    0.58
     convincing
    0.58
    lins
    0.58
    conv
    0.58
     Krug
    0.57
    ç«
    0.57
    Act Density 0.387%

    No Known Activations