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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irling
    -0.16
    è¾°
    -0.15
    dit
    -0.15
     Nó
    -0.14
    erot
    -0.14
    esson
    -0.14
     nợ
    -0.14
    éli
    -0.14
    amu
    -0.14
    anten
    -0.14
    POSITIVE LOGITS
    å¹²
    0.14
    ITIES
    0.14
    ias
    0.13
    809
    0.13
    863
    0.13
    Interior
    0.13
     Bust
    0.13
    ãģ¾ãģļ
    0.13
    AYS
    0.13
    ress
    0.13
    Act Density 0.077%

    No Known Activations