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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "forgive" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñij
    -0.17
    785
    -0.15
    wise
    -0.15
    ially
    -0.15
    eli
    -0.15
    iations
    -0.14
    maker
    -0.14
    apa
    -0.14
    theory
    -0.14
    bestos
    -0.14
    POSITIVE LOGITS
    otten
    0.27
    unately
    0.24
    bidden
    0.19
    ibly
    0.18
     sake
    0.18
    otton
    0.18
    closure
    0.18
     Nhĩ
    0.17
    rightness
    0.17
    feit
    0.17
    Act Density 0.038%

    No Known Activations