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

    Neuronpedia

    INDEX
    Explanations

    quotes that need citations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "citation" or references to citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quer
    -0.80
    ths
    -0.67
    olen
    -0.63
    obar
    -0.62
    azes
    -0.57
    ãĥ£
    -0.57
    atars
    -0.57
    gd
    -0.57
     diapers
    -0.56
    pora
    -0.56
    POSITIVE LOGITS
    itation
    1.07
    itations
    0.88
    itative
    0.82
    hower
    0.79
     Citation
    0.76
    eers
    0.71
    itating
    0.70
    ariat
    0.69
     Casting
    0.68
    iting
    0.68
    Act Density 0.020%

    No Known Activations