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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äįit
    -0.17
    èo
    -0.15
    ì§ĵ
    -0.14
    auge
    -0.14
    sizeof
    -0.14
     inmate
    -0.14
    Soft
    -0.14
    lemen
    -0.14
    ouncer
    -0.14
    èľľ
    -0.14
    POSITIVE LOGITS
    imit
    0.16
     altogether
    0.15
    γή
    0.15
     Boeh
    0.15
     Hath
    0.14
     away
    0.14
     trailing
    0.13
     khá»ıi
    0.13
    ichick
    0.13
     SON
    0.13
    Act Density 0.344%

    No Known Activations