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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.84
    ãĥ¡
    -0.68
    ãĥĪ
    -0.62
    taboola
    -0.61
     Krish
    -0.56
    Topic
    -0.55
     phosph
    -0.55
    ãĤ¹
    -0.54
    ãĥ¼ãĤ¯
    -0.54
    è£ħ
    -0.54
    POSITIVE LOGITS
    llor
    0.84
    ourke
    0.80
    ullivan
    0.76
    uliffe
    0.74
    inion
    0.69
    herty
    0.68
    UFF
    0.68
    aeda
    0.66
    ATA
    0.66
    oyer
    0.65
    Act Density 0.070%

    No Known Activations