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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to fiber-related terms and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pity
    -0.69
     undone
    -0.62
    isters
    -0.61
    ĸļ
    -0.60
    olulu
    -0.58
    abortion
    -0.57
     Shack
    -0.57
     nont
    -0.57
     Mosul
    -0.57
     ath
    -0.57
    POSITIVE LOGITS
    iber
    1.26
    tarian
    1.07
    glass
    1.01
    tarians
    0.90
    glas
    0.86
    ilib
    0.83
    oad
    0.81
    JJ
    0.80
    culus
    0.79
    ãĥ¼ãĤ¯
    0.78
    Act Density 0.005%

    No Known Activations