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

    Neuronpedia

    INDEX
    Explanations

    references to studies and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arger
    -0.16
    777
    -0.15
    ÙĦÙħ
    -0.14
    hari
    -0.14
    _colour
    -0.14
    اÙĪ
    -0.14
     Hank
    -0.14
    umping
    -0.14
    eger
    -0.13
    isman
    -0.13
    POSITIVE LOGITS
    (*)(
    0.15
    rir
    0.15
    inke
    0.15
    inki
    0.15
    DMI
    0.14
    ESCO
    0.14
    езда
    0.14
     behalf
    0.14
    ewe
    0.14
    okus
    0.14
    Act Density 0.051%

    No Known Activations