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

    Neuronpedia

    INDEX
    Explanations

    references to individual strengths and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otton
    -0.17
    arin
    -0.15
    igg
    -0.14
    stants
    -0.14
     Finger
    -0.14
     Kral
    -0.14
    pany
    -0.14
    apur
    -0.14
    CLUDING
    -0.14
    WithEmail
    -0.14
    POSITIVE LOGITS
    алом
    0.15
    yah
    0.15
    _HAL
    0.14
    utzer
    0.14
    _IA
    0.14
    ably
    0.14
     Swinger
    0.14
     Caval
    0.14
    ceae
    0.13
     erect
    0.13
    Act Density 0.109%

    No Known Activations