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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "there" indicating presence or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esian
    -0.22
    greSQL
    -0.22
    tlement
    -0.21
    ton
    -0.20
    odore
    -0.18
    lehem
    -0.17
    anmar
    -0.17
    quarters
    -0.17
    sgiving
    -0.16
    smouth
    -0.16
    POSITIVE LOGITS
    by
    0.43
    after
    0.39
    upon
    0.27
    in
    0.24
    bye
    0.22
    alone
    0.22
    fore
    0.21
    Upon
    0.21
    ina
    0.21
    ford
    0.21
    Act Density 0.072%

    No Known Activations