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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional reactions or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lÃŃ
    -0.16
     Naw
    -0.15
    ¶Į
    -0.15
    bursement
    -0.15
    sit
    -0.15
    _PATCH
    -0.15
    fak
    -0.14
    opoulos
    -0.14
    ungle
    -0.13
    olin
    -0.13
    POSITIVE LOGITS
    illo
    0.15
    Ñĥв
    0.15
    .TryParse
    0.15
    ãĤ¹ãĤ¿ãĥ¼
    0.15
    robe
    0.15
    ayım
    0.14
    vrier
    0.13
    rog
    0.13
    iris
    0.13
     Gins
    0.13
    Act Density 0.037%

    No Known Activations