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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal sentences and punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.17
    esty
    -0.16
    teen
    -0.16
    avez
    -0.15
    ser
    -0.15
    ç·Ĵ
    -0.15
    ater
    -0.15
    å¯Ħ
    -0.15
    elters
    -0.14
    //{{
    -0.14
    POSITIVE LOGITS
    inals
    0.20
    urrect
    0.16
    ments
    0.16
    e
    0.15
    sov
    0.15
    apel
    0.15
    ables
    0.14
    Structure
    0.14
    325
    0.14
    break
    0.14
    Act Density 0.008%

    No Known Activations