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

    Neuronpedia

    INDEX
    Explanations

    emotions related to anger and dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.78
    ulhu
    -0.72
    sac
    -0.70
    Interstitial
    -0.63
    ample
    -0.62
    akeru
    -0.62
     livest
    -0.61
    Untitled
    -0.61
    ftime
    -0.59
    EStreamFrame
    -0.59
    POSITIVE LOGITS
     themselves
    0.74
     passionately
    0.70
     eagerly
    0.69
     loudly
    0.68
     seeing
    0.67
     bitterly
    0.66
     hearing
    0.66
    joy
    0.65
     furiously
    0.64
     vehemently
    0.64
    Act Density 0.136%

    No Known Activations