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

    Neuronpedia

    INDEX
    Explanations

    words related to cutting or removing something

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases containing the substring "st"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -1.08
    ļéĨĴ
    -0.82
    mingham
    -0.82
    EStream
    -0.79
    thodox
    -0.74
    veyard
    -0.74
    metry
    -0.73
    DragonMagazine
    -0.73
    hound
    -0.71
    iferation
    -0.70
    POSITIVE LOGITS
    uffed
    1.11
    ength
    1.00
    roller
    0.97
    itched
    0.96
    alker
    0.95
    aves
    0.93
    rolled
    0.89
    inging
    0.89
    amped
    0.89
    igm
    0.89
    Act Density 0.019%

    No Known Activations