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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exposure or being exposed to something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "exposed" related to various contexts or risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.84
    widget
    -0.77
    translation
    -0.68
    driver
    -0.67
    notations
    -0.66
    signed
    -0.66
    rollers
    -0.66
    tenance
    -0.64
    employed
    -0.64
    swers
    -0.64
    POSITIVE LOGITS
     radiation
    0.85
     fend
    0.84
     acid
    0.83
     fire
    0.81
    othy
    0.78
     sunlight
    0.76
     acids
    0.76
     gunfire
    0.74
     ozone
    0.73
    asted
    0.73
    Act Density 0.077%

    No Known Activations