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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.33
    2:0.04
    3:0.09
    4:0.04
    5:0.06
    6:0.03
    7:0.09
    8:0.12
    9:0.02
    10:0.04
    11:0.06
    Negative Logits
     millenn
    -2.95
    orescent
    -2.94
    orously
    -2.68
    orescence
    -2.63
     continual
    -2.62
     ourselves
    -2.62
     truly
    -2.52
     exhibitions
    -2.50
    ram
    -2.49
    士
    -2.46
    POSITIVE LOGITS
     Arkansas
    3.46
    ワ
    3.15
    California
    3.10
     Idaho
    3.08
     Mesa
    2.96
     Colorado
    2.89
    Ark
    2.88
    aska
    2.85
     Arizona
    2.81
     47
    2.75
    Act Density 0.001%

    No Known Activations