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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to being physically exposed or having exposure to various elements or environments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exposed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orio
    -0.70
    illard
    -0.67
    othe
    -0.66
    tesy
    -0.65
    wise
    -0.63
    rocal
    -0.62
    rones
    -0.62
    erva
    -0.61
    rolley
    -0.61
    otor
    -0.61
    POSITIVE LOGITS
     exposed
    1.00
     Breach
    0.84
     Exposure
    0.82
    м
    0.80
    çīĪ
    0.77
     exposing
    0.76
    é¾
    0.75
     exposes
    0.73
    xual
    0.73
    Versions
    0.73
    Act Density 0.012%

    No Known Activations