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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or expressions indicating hypothetical situations

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

    if then condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.56
    UnifiedTopology
    -0.49
    udayaan
    -0.45
     ModelExpression
    -0.44
    abinieri
    -0.43
     Waray
    -0.42
    {'
    -0.42
     Familienname
    -0.41
    KEYCODE
    -0.41
    -0.40
    POSITIVE LOGITS
    すると
    1.13
    ると
    1.07
    すと
    1.04
    されると
    0.96
    くと
    0.95
    けると
    0.93
    えると
    0.90
    くると
    0.85
    になると
    0.83
    があると
    0.77
    Act Density 0.009%

    No Known Activations