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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter "W"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APH
    -0.16
    vetica
    -0.16
    dma
    -0.15
    zan
    -0.15
    erosis
    -0.14
    úp
    -0.14
    temporary
    -0.14
    upil
    -0.14
    amento
    -0.14
    iplina
    -0.14
    POSITIVE LOGITS
    right
    0.34
    iggins
    0.31
    eller
    0.31
    inters
    0.31
    ylie
    0.29
    ray
    0.29
    irth
    0.29
    atters
    0.29
    ampler
    0.28
    iese
    0.28
    Act Density 0.026%

    No Known Activations