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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msp
    -0.17
    stime
    -0.17
    udeau
    -0.17
    رÙĪس
    -0.16
    tsky
    -0.15
    elage
    -0.15
    okus
    -0.14
    itou
    -0.14
    inic
    -0.14
    Segue
    -0.14
    POSITIVE LOGITS
     else
    0.19
     simply
    0.17
    anges
    0.16
     rather
    0.15
    ooter
    0.15
    naments
    0.15
    imas
    0.15
     maybe
    0.15
     indeed
    0.14
     Or
    0.14
    Act Density 0.065%

    No Known Activations