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

    Neuronpedia

    INDEX
    Explanations

    words related to disorder and confusion

    oai_token-act-pair · gpt-3.5-turbo

    references to disorder or turmoil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ents
    -0.82
    arers
    -0.74
    phies
    -0.74
    ighed
    -0.73
    alties
    -0.73
    bors
    -0.73
    istle
    -0.72
    aired
    -0.71
    Personal
    -0.71
    odor
    -0.71
    POSITIVE LOGITS
     pandemonium
    1.18
     chaos
    1.12
     mayhem
    0.94
     havoc
    0.90
    cffff
    0.85
     unfold
    0.78
     ensued
    0.78
    INESS
    0.77
     redes
    0.77
     disorder
    0.76
    Act Density 0.007%

    No Known Activations