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

    Neuronpedia

    INDEX
    Explanations

    interrogative terms that indicate questioning or choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uese
    -0.15
    ières
    -0.14
    uros
    -0.14
    filer
    -0.14
    ạn
    -0.14
    Extreme
    -0.14
    aro
    -0.14
    sson
    -0.14
    ings
    -0.14
    shit
    -0.13
    POSITIVE LOGITS
    soever
    0.22
    /how
    0.18
     Ñģаме
    0.16
    pher
    0.15
    wyn
    0.14
     именно
    0.14
    ëĵł
    0.14
    irl
    0.14
    _registro
    0.14
    ваÑĢ
    0.14
    Act Density 0.035%

    No Known Activations