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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics and public figures

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scroll
    -0.77
    aughtered
    -0.77
    jandro
    -0.76
    rones
    -0.76
    aughters
    -0.74
    inav
    -0.73
    ipeg
    -0.72
    urry
    -0.72
    letal
    -0.72
     Starts
    -0.72
    POSITIVE LOGITS
     bluff
    1.29
     joking
    1.29
     exagger
    1.27
     kidding
    1.27
     delusional
    1.22
     guilty
    1.19
     trying
    1.16
     unaware
    1.16
     aware
    1.14
     sincere
    1.13
    Act Density 0.285%

    No Known Activations