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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or concern in decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afia
    -0.15
    寿
    -0.14
    ανδ
    -0.14
     ham
    -0.14
     plans
    -0.14
    Ã
    -0.14
    aveled
    -0.14
     Fathers
    -0.13
    aris
    -0.13
     yaz
    -0.13
    POSITIVE LOGITS
     derec
    0.17
    ái
    0.16
    imuth
    0.16
    rijk
    0.14
    oze
    0.14
    ROKE
    0.14
    ean
    0.14
    QRST
    0.14
    ặng
    0.14
    oux
    0.14
    Act Density 0.093%

    No Known Activations