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

    Neuronpedia

    INDEX
    Explanations

    instances of commas or punctuation marks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolis
    -0.16
    rapper
    -0.16
    604
    -0.15
    andler
    -0.15
     DEALINGS
    -0.14
    ÄĽÅ¾
    -0.14
    ANDLE
    -0.14
    lope
    -0.14
    çĭIJ
    -0.14
    /includes
    -0.14
    POSITIVE LOGITS
    sett
    0.17
    essen
    0.17
    ALER
    0.15
    ucz
    0.15
    Ł
    0.15
    erts
    0.15
    βε
    0.14
    egal
    0.14
    aler
    0.14
    MP
    0.14
    Act Density 0.018%

    No Known Activations