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

    Neuronpedia

    INDEX
    Explanations

    expressions of discontent or negativity

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

    expressing pity or regret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     movimientos
    -0.41
     przede
    -0.35
     <<<<<<<<<<<<<<
    -0.34
     Erscheinung
    -0.34
     invokingState
    -0.32
     HasFactory
    -0.32
     manifestación
    -0.30
     humedad
    -0.30
     moments
    -0.29
     llenos
    -0.29
    POSITIVE LOGITS
    bad
    0.75
     bad
    0.72
     Pity
    0.70
    Bad
    0.69
    ValueStyle
    0.65
    ftagPool
    0.65
     BAD
    0.65
     Bad
    0.64
    pity
    0.63
    BAD
    0.62
    Act Density 0.002%

    No Known Activations