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

    Neuronpedia

    INDEX
    Explanations

    words related to proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "g" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.85
    tenance
    -0.82
     Dame
    -0.72
    terday
    -0.69
    ĸļ
    -0.68
     Continued
    -0.66
     Ruins
    -0.65
     questioning
    -0.65
     retrospect
    -0.64
     Exile
    -0.64
    POSITIVE LOGITS
    ulp
    1.25
    rosso
    1.15
    asp
    1.12
    idd
    1.10
    ourmet
    1.10
    aret
    1.09
    agging
    1.07
    amed
    1.06
    iggle
    1.05
    endered
    1.05
    Act Density 0.021%

    No Known Activations