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

    Neuronpedia

    INDEX
    Explanations

    contrastive conjunctions and conditional phrases

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

    whereas or while

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !*\
    -0.45
    +#+
    -0.38
    mybatisplus
    -0.37
    řev
    -0.37
    TAWA
    -0.35
    tagHelperRunner
    -0.35
     StringTokenizer
    -0.35
    DockStyle
    -0.34
    callee
    -0.34
     bom
    -0.33
    POSITIVE LOGITS
    exitRule
    0.50
     makeStyles
    0.48
    nobyl
    0.48
    Während
    0.47
     مشين
    0.46
    getMinutes
    0.45
    eradish
    0.44
     Mentre
    0.44
     Winaray
    0.44
    wijl
    0.43
    Act Density 0.082%

    No Known Activations