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

    Neuronpedia

    INDEX
    Explanations

    elements associated with emphasis, conditionals, and negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ĩu
    -0.17
    ">//
    -0.15
    idf
    -0.15
    pollo
    -0.15
     Sheet
    -0.14
     hala
    -0.14
     Dalton
    -0.14
    idl
    -0.14
    asic
    -0.14
    asn
    -0.14
    POSITIVE LOGITS
    åIJ¦
    0.16
    á»ĭch
    0.15
    еÑģÑĤв
    0.15
    .anchor
    0.14
     otherwise
    0.14
    él
    0.14
     Fav
    0.14
    ICS
    0.14
    cox
    0.14
    ector
    0.13
    Act Density 0.001%

    No Known Activations