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

    Neuronpedia

    INDEX
    Explanations

    words related to intense anger or outrage

    oai_token-act-pair · gpt-3.5-turbo

    words conveying strong feelings of anger or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glas
    -0.98
    opic
    -0.88
    aky
    -0.82
    sites
    -0.81
    pmwiki
    -0.80
    omaly
    -0.79
    ococ
    -0.76
    icipated
    -0.74
    akes
    -0.73
    fman
    -0.73
    POSITIVE LOGITS
     indignation
    0.92
     furious
    0.91
     uproar
    0.76
     homophobic
    0.74
     outburst
    0.73
     outraged
    0.73
     upset
    0.72
    NESS
    0.71
     angry
    0.71
     shouts
    0.70
    Act Density 0.022%

    No Known Activations