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

    Neuronpedia

    INDEX
    Explanations

    hashtags or identifiers related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Friendship
    -0.15
    å®ĭ
    -0.15
    805
    -0.14
    ÑĦоÑĢ
    -0.14
     Freund
    -0.14
    elpers
    -0.14
    uild
    -0.13
    [].
    -0.13
    xx
    -0.13
    792
    -0.13
    POSITIVE LOGITS
    太éĥİ
    0.16
    鬼
    0.15
    awei
    0.15
     Garr
    0.14
    åde
    0.14
    andler
    0.13
    mate
    0.13
    ento
    0.13
    URNS
    0.13
    ThanOr
    0.13
    Act Density 0.023%

    No Known Activations