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

    Neuronpedia

    INDEX
    Explanations

    references to essays, articles, and related writing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivec
    -0.19
    tok
    -0.16
    -пÑĢав
    -0.16
     span
    -0.14
     patter
    -0.14
     Fiscal
    -0.14
    oller
    -0.14
     couch
    -0.14
    pare
    -0.14
    ihan
    -0.14
    POSITIVE LOGITS
     obce
    0.17
    borough
    0.16
    ãģ£ãģ
    0.15
    اذا
    0.15
    alist
    0.15
    istes
    0.14
    vers
    0.14
    oph
    0.14
    iste
    0.14
    acen
    0.14
    Act Density 0.915%

    No Known Activations