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

    Neuronpedia

    INDEX
    Explanations

    emotional and subjective reactions to social or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.65
    :])
    -0.54
    stination
    -0.54
    楔
    -0.53
     Administrativna
    -0.53
     kiệm
    -0.52
     مؤرشف
    -0.51
     dependencia
    -0.50
     Laur
    -0.50
    ()?;
    -0.49
    POSITIVE LOGITS
     upset
    1.08
     annoyed
    0.98
     displeased
    0.95
     disturbed
    0.94
     disappointed
    0.93
     frustrated
    0.92
     angered
    0.92
     irritated
    0.92
     outraged
    0.92
     furious
    0.91
    Act Density 0.283%

    No Known Activations