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

    words related to disorder and turmoil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icrobial
    -0.75
    estone
    -0.73
    estones
    -0.71
    izations
    -0.69
    bey
    -0.67
    ĻĤ
    -0.67
    aton
    -0.66
    val
    -0.66
    itor
    -0.64
    cium
    -0.63
    POSITIVE LOGITS
     engulf
    0.91
     arose
    0.83
     caused
    0.82
     arising
    0.82
     stemming
    0.81
     ensued
    0.81
    Downloadha
    0.80
     abound
    0.80
     arises
    0.78
     surrounding
    0.77
    Act Density 0.074%

    No Known Activations