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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong negative emotions, particularly anger and frustration

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

    expressions of anger or rage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.58
     tiguan
    -0.56
     ErrIntOverflow
    -0.56
    HasAnnotation
    -0.55
     ligiloj
    -0.55
    Datuak
    -0.54
    :✨
    -0.53
    EndGlobalSection
    -0.52
     nahilalakip
    -0.51
     tartalomajánló
    -0.51
    POSITIVE LOGITS
     angry
    0.79
     colère
    0.73
     anger
    0.69
     annoyed
    0.69
    angry
    0.68
    Angry
    0.67
     angered
    0.67
     indignant
    0.66
    怒
    0.66
     furious
    0.65
    Act Density 0.027%

    No Known Activations