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

    Neuronpedia

    INDEX
    Explanations

    indicators of time, place, and context within legal or formal writing

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

    words indicating prior or conditional states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.76
     surla
    -0.59
    enterOuterAlt
    -0.54
    delwed
    -0.53
     mesmas
    -0.52
    épaisseur
    -0.52
    tyczne
    -0.50
    كويكب
    -0.50
     uș
    -0.49
     särsk
    -0.48
    POSITIVE LOGITS
     EconPapers
    0.53
     often
    0.52
     historically
    0.52
     oft
    0.51
     hitherto
    0.49
     nakalista
    0.48
     rarely
    0.48
    ually
    0.47
     heretofore
    0.46
     widely
    0.45
    Act Density 0.130%

    No Known Activations