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

    Neuronpedia

    INDEX
    Explanations

    phrases related to belief, faith, or conviction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to belief or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reinstated
    -0.66
     phased
    -0.61
     overseen
    -0.61
     levied
    -0.59
     federation
    -0.58
    FML
    -0.58
    abouts
    -0.58
     enforced
    -0.57
     ratified
    -0.57
     reluct
    -0.57
    POSITIVE LOGITS
     selfies
    0.65
    TextColor
    0.63
    rouse
    0.61
    rome
    0.61
    ogly
    0.58
     webcam
    0.57
    姫
    0.57
    ĸļ
    0.56
    picture
    0.56
     landscapes
    0.56
    Act Density 0.991%

    No Known Activations