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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and choosing sides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acid
    -0.17
    acidad
    -0.16
    rant
    -0.16
    ntag
    -0.15
    ẩy
    -0.15
    виж
    -0.15
    PostExecute
    -0.15
    idders
    -0.15
    bild
    -0.14
    hiba
    -0.14
    POSITIVE LOGITS
     finally
    0.16
    éľ²
    0.16
    決
    0.15
    æ»
    0.15
    ặn
    0.15
     Casc
    0.15
    ırak
    0.15
    perPage
    0.15
    ë°©
    0.14
    ç¾
    0.14
    Act Density 0.287%

    No Known Activations