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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and their surrounding context in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Str
    -0.14
     Stat
    -0.14
     eo
    -0.14
    aec
    -0.14
    iffs
    -0.14
     Ont
    -0.14
     Sp
    -0.14
     Ent
    -0.14
     ln
    -0.14
    *e
    -0.14
    POSITIVE LOGITS
    ménÄĽ
    0.30
    reak
    0.23
    lÃŃb
    0.21
    nap
    0.21
    oble
    0.20
    vůli
    0.20
    roz
    0.20
    jed
    0.20
    zá
    0.19
    nad
    0.19
    Act Density 0.020%

    No Known Activations