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

    Neuronpedia

    INDEX
    Explanations

    words related to protest movements or activism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Demon" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tta
    -0.70
    ippi
    -0.67
    RAFT
    -0.65
    uberty
    -0.64
    giving
    -0.63
     scarce
    -0.61
     saline
    -0.60
     Kinnikuman
    -0.60
     Robertson
    -0.59
    ãģ¦
    -0.59
    POSITIVE LOGITS
    stration
    1.30
    demon
    0.97
     Demon
    0.96
    strate
    0.94
    Demon
    0.90
    ciples
    0.78
    iac
    0.76
    iques
    0.76
    inators
    0.75
    strike
    0.75
    Act Density 0.006%

    No Known Activations