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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease of action or simplicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unga
    -0.18
    rani
    -0.17
     blank
    -0.15
    Blank
    -0.14
    INTEGER
    -0.14
    dek
    -0.14
    nty
    -0.14
    ваÑı
    -0.13
    Mapper
    -0.13
     tick
    -0.13
    POSITIVE LOGITS
     dÃłng
    0.16
     Easily
    0.16
     Donovan
    0.14
     Donna
    0.14
    antt
    0.14
    ŃĶ
    0.14
    BarButton
    0.14
     Ùħشار
    0.14
    ahlen
    0.14
    ause
    0.14
    Act Density 0.049%

    No Known Activations