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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numeric values or ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eros
    -0.17
    ischer
    -0.17
    oola
    -0.16
    ãĥIJãĤ¤
    -0.14
     Hale
    -0.14
    tica
    -0.14
    crast
    -0.14
    ost
    -0.14
    alley
    -0.14
    orro
    -0.14
    POSITIVE LOGITS
    _deps
    0.16
    wil
    0.16
    .jasper
    0.16
    chn
    0.14
    rip
    0.14
    QRST
    0.14
    anlar
    0.14
    anging
    0.14
    ars
    0.14
    zing
    0.13
    Act Density 0.005%

    No Known Activations