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

    Neuronpedia

    INDEX
    Explanations

    locations or proper nouns related to specific places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onut
    -0.88
    icol
    -0.80
    umn
    -0.77
    µ
    -0.74
    ©¶æ
    -0.69
    esity
    -0.69
    lasses
    -0.66
    icho
    -0.64
    çīĪ
    -0.63
    sam
    -0.63
    POSITIVE LOGITS
     Lann
    0.94
    ion
    0.90
    enger
    0.87
    afort
    0.84
    inian
    0.76
    igate
    0.71
    lain
    0.70
    yards
    0.68
    ribut
    0.66
     Malfoy
    0.66
    Act Density 0.046%

    No Known Activations