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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anine
    -0.17
     Comics
    -0.16
     Lage
    -0.15
    .MaxLength
    -0.15
    antz
    -0.13
     Fucking
    -0.13
    NaN
    -0.13
    å»·
    -0.13
    ÃŃas
    -0.13
    tpl
    -0.13
    POSITIVE LOGITS
    ched
    0.20
     same
    0.17
    278
    0.17
    icky
    0.15
    110
    0.15
    urb
    0.15
    ika
    0.14
    ellar
    0.14
    ertia
    0.14
    aired
    0.14
    Act Density 0.135%

    No Known Activations