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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vana
    -0.15
     Bris
    -0.15
    ones
    -0.15
     late
    -0.14
     Arb
    -0.14
    astos
    -0.14
    oner
    -0.14
    ocket
    -0.14
    cete
    -0.14
    <Application
    -0.14
    POSITIVE LOGITS
    inton
    0.18
    ï¸
    0.17
    oz
    0.16
    igin
    0.16
    ripple
    0.15
    ocre
    0.15
    ingle
    0.15
     addCriterion
    0.15
    æı¡
    0.15
    essed
    0.14
    Act Density 0.015%

    No Known Activations