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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experimental results and data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    617
    -0.16
    698
    -0.15
    647
    -0.15
     Reservation
    -0.14
    [
    -0.14
    _HDR
    -0.14
    xin
    -0.14
    exo
    -0.14
     pointers
    -0.14
    S
    -0.13
    POSITIVE LOGITS
     respectively
    0.18
    agara
    0.18
    ç§
    0.16
    akov
    0.15
    sse
    0.14
     éĸ
    0.14
    Ñĭл
    0.14
    ueur
    0.14
    æݧ
    0.14
    κο
    0.14
    Act Density 0.099%

    No Known Activations