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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "there"

    oai_token-act-pair · gpt-3.5-turbo

    the word "there."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CJ
    -0.72
     cogn
    -0.67
     favour
    -0.63
     cent
    -0.60
     ±
    -0.58
     franc
    -0.57
     Aden
    -0.57
     actionGroup
    -0.57
     tolerant
    -0.56
     Erit
    -0.55
    POSITIVE LOGITS
    abouts
    1.15
    upon
    1.03
    ngth
    0.86
    geist
    0.85
    ket
    0.78
    hovah
    0.77
    after
    0.75
    fore
    0.74
    esson
    0.74
    leased
    0.73
    Act Density 0.142%

    No Known Activations