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

    Neuronpedia

    INDEX
    Explanations

    references to cost savings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udad
    -0.17
    ppo
    -0.16
    änner
    -0.16
    PTY
    -0.15
    uth
    -0.15
    еÑģÑı
    -0.15
    utow
    -0.15
    Histogram
    -0.15
    ĽĦ
    -0.15
    aguay
    -0.15
    POSITIVE LOGITS
    land
    0.17
    itin
    0.15
    aupt
    0.15
    ÑĢив
    0.15
    vang
    0.14
    dra
    0.14
    ssa
    0.13
    inton
    0.13
    enc
    0.13
    wick
    0.13
    Act Density 0.008%

    No Known Activations