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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and structure in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansi
    -0.17
    antz
    -0.17
     Vac
    -0.14
    Nam
    -0.14
    atoi
    -0.13
    Vs
    -0.13
     Nam
    -0.13
    nam
    -0.13
     Hardcore
    -0.13
    uling
    -0.13
    POSITIVE LOGITS
     noun
    0.21
     adj
    0.20
     verb
    0.19
    Verb
    0.19
     Syn
    0.18
    IPA
    0.18
    verb
    0.18
    adj
    0.17
    .adj
    0.17
    USAGE
    0.17
    Act Density 0.086%

    No Known Activations