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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation commonly used in lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows/precedes a comma

    np_acts-logits-general · gemini-2.0-flash

    list items separated by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.61
     BIBSYS
    -0.60
     initWithFrame
    -0.59
    Titled
    -0.58
    Hozzáférés
    -0.58
     tege
    -0.54
    َم
    -0.53
     acu
    -0.52
     EXCLUS
    -0.52
    ($__
    -0.51
    POSITIVE LOGITS
     etc
    1.26
    etc
    0.97
     usw
    0.92
    などなど
    0.89
     Etc
    0.80
     Roskov
    0.80
     그리고
    0.78
     ...)
    0.78
     …)
    0.77
    <bos>
    0.72
    Act Density 0.612%

    No Known Activations