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

    Neuronpedia

    INDEX
    Explanations

    statements expressing negativity or dislike

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

    at all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.49
     étoit
    -0.46
     étoient
    -0.45
     ModelExpression
    -0.45
     otomatig
    -0.42
     disambiguazione
    -0.41
     kiệm
    -0.41
    verwijspagina
    -0.41
     auroit
    -0.40
    -0.40
    POSITIVE LOGITS
     ogóle
    0.68
     Totally
    0.64
    bentar
    0.62
    Totally
    0.60
     vůbec
    0.59
     affatto
    0.59
     Really
    0.59
     totally
    0.59
    totally
    0.58
    Really
    0.57
    Act Density 0.004%

    No Known Activations