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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions that indicate relationships or connections in text

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

    variations to this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WindowConstants
    -0.38
    iocene
    -0.38
    sle
    -0.36
    営業時間
    -0.35
     STA
    -0.35
     NUE
    -0.35
     rates
    -0.35
    はじめまして
    -0.35
     rate
    -0.35
     innovative
    -0.35
    POSITIVE LOGITS
    (!__
    0.68
    ValueStyle
    0.59
     MainAxisSize
    0.55
     ब्रेकडाउन
    0.54
    aarrggbb
    0.54
     Infórmanos
    0.53
    colgante
    0.52
     للمعارف
    0.52
     المعيارى
    0.51
    postsleuth
    0.50
    Act Density 0.058%

    No Known Activations