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

    Neuronpedia

    INDEX
    Explanations

    terms associated with negativity or unpleasantness

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

    sour, sourdough, sourcing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MatDialog
    -0.58
     matrícula
    -0.55
    Vidite
    -0.53
    enumii
    -0.53
    ⓧ
    -0.52
    pezi
    -0.51
     eventId
    -0.49
    èlement
    -0.47
     MainAxisSize
    -0.47
     maș
    -0.47
    POSITIVE LOGITS
     sour
    2.09
    sour
    2.02
     Sour
    2.00
    Sour
    1.98
     Source
    0.79
     sourdough
    0.79
     Sourcing
    0.78
     SOURCE
    0.77
     Sauer
    0.72
     sourcing
    0.69
    Act Density 0.002%

    No Known Activations