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

    Neuronpedia

    INDEX
    Explanations

    instances of strings or text formatting symbols in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igits
    -0.17
     eskort
    -0.16
    INVAL
    -0.15
     Blanc
    -0.15
    Clone
    -0.14
    avou
    -0.14
    pora
    -0.14
    å²
    -0.14
    emics
    -0.14
     likewise
    -0.14
    POSITIVE LOGITS
     +
    0.24
    }${
    0.18
    concat
    0.16
     Conc
    0.16
    .concat
    0.15
    Äı
    0.15
    ÂĿ
    0.15
     "\""
    0.14
     concat
    0.14
    annes
    0.14
    Act Density 0.042%

    No Known Activations