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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and requests for help

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

    thanks followed by edit or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gra
    -0.39
     enriched
    -0.35
     einz
    -0.35
     bo
    -0.33
     superior
    -0.33
     dismissed
    -0.32
     suppressed
    -0.32
     stimm
    -0.32
    unregister
    -0.32
     pass
    -0.32
    POSITIVE LOGITS
     utafitiHapana
    0.74
     فريبيس
    0.59
     HasFactory
    0.55
    endcsname
    0.54
     requests
    0.53
     $_"
    0.52
    exitRule
    0.51
    ActionCreators
    0.51
     ब्रेकडाउन
    0.50
    IVEREF
    0.49
    Act Density 0.066%

    No Known Activations