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

    Neuronpedia

    INDEX
    Explanations

    punctuation and emoticons used in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abar
    -0.16
    #
    -0.15
    'gc
    -0.15
    <source
    -0.15
    thane
    -0.14
    245
    -0.14
    ÑĢаÑħ
    -0.14
    nez
    -0.14
    zier
    -0.14
    etler
    -0.13
    POSITIVE LOGITS
    D
    0.25
    P
    0.23
    DDD
    0.22
    (↵
    0.21
    Ãŀ
    0.20
    p
    0.20
    þ
    0.20
    o
    0.20
    O
    0.19
    PPP
    0.19
    Act Density 0.012%

    No Known Activations