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

    Neuronpedia

    INDEX
    Explanations

    expressions of comparison and degrees of expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĿĬ
    -0.18
     Anast
    -0.16
    æ®Ĭ
    -0.15
    antan
    -0.15
    remen
    -0.14
    lapping
    -0.14
    .datatables
    -0.14
    baum
    -0.14
    apon
    -0.13
     equ
    -0.13
    POSITIVE LOGITS
    _Move
    0.17
    otos
    0.15
    urma
    0.14
    Ńå·ŀ
    0.14
     cuent
    0.14
    @student
    0.14
    aura
    0.14
    antis
    0.14
    emax
    0.14
    geist
    0.14
    Act Density 0.234%

    No Known Activations