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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "by" indicating authorship or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erson
    -0.15
    رج
    -0.15
    evin
    -0.14
     Hancock
    -0.14
    Coder
    -0.14
    ÑģÑĤин
    -0.14
    à¸ģลาà¸ĩ
    -0.14
    nÃŃ
    -0.14
    045
    -0.14
    릿
    -0.13
    POSITIVE LOGITS
    isi
    0.20
     Various
    0.17
     anon
    0.17
    ajs
    0.16
    uddle
    0.15
     Anonymous
    0.15
     Feld
    0.14
    saldo
    0.14
    igs
    0.14
    inha
    0.14
    Act Density 0.054%

    No Known Activations