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

    Neuronpedia

    INDEX
    Explanations

    word patterns that include "att" or "ott" at various positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.19
    ãģįãģŁ
    -0.19
    ove
    -0.18
    pen
    -0.18
    rics
    -0.18
    ook
    -0.17
    ric
    -0.17
    oho
    -0.16
    rus
    -0.16
    ru
    -0.16
    POSITIVE LOGITS
    sville
    0.24
    orney
    0.24
    sburgh
    0.22
    anooga
    0.22
    orneys
    0.22
    t
    0.20
    ahoo
    0.20
    les
    0.20
    endor
    0.20
    erson
    0.19
    Act Density 0.031%

    No Known Activations