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

    Neuronpedia

    INDEX
    Explanations

    words related to disorder, confusion, and panic

    oai_token-act-pair · gpt-3.5-turbo

    references to chaos and disorder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.91
    alties
    -0.88
    istle
    -0.78
    odor
    -0.78
    phies
    -0.77
    icrobial
    -0.77
    ovember
    -0.74
    berman
    -0.73
    pointers
    -0.72
    glas
    -0.70
    POSITIVE LOGITS
     havoc
    0.96
     pandemonium
    0.96
     chaos
    0.91
    INESS
    0.91
     unfold
    0.81
     disorder
    0.77
     ensued
    0.74
     mayhem
    0.74
     engulf
    0.72
     Chaos
    0.71
    Act Density 0.018%

    No Known Activations