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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the location or existence of a particular thing in different regions

    oai_token-act-pair · gpt-3.5-turbo

    a reference to current events or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategory
    -0.87
    obbies
    -0.85
    é¾
    -0.80
    ossal
    -0.76
    姫
    -0.75
    obby
    -0.72
    éļ
    -0.71
    apon
    -0.71
    outube
    -0.70
    rouse
    -0.70
    POSITIVE LOGITS
    der
    0.67
    erved
    0.65
     (-
    0.64
    cession
    0.64
     Iraqi
    0.62
     Manafort
    0.62
     Downs
    0.61
    reflect
    0.60
     âĪĴ
    0.60
    Van
    0.58
    Act Density 0.000%

    No Known Activations