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

    Neuronpedia

    INDEX
    Explanations

    words that signify conditions, limitations, or qualifiers in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìĦŃ
    -0.15
    Æ°a
    -0.15
    yntax
    -0.15
    730
    -0.15
     Neville
    -0.14
    RF
    -0.14
    elere
    -0.14
    shr
    -0.14
    ÑĢави
    -0.14
     piger
    -0.13
    POSITIVE LOGITS
    rs
    0.15
    .EventQueue
    0.15
     sting
    0.15
    land
    0.14
     Bris
    0.14
     modern
    0.14
    otta
    0.14
    ers
    0.14
    ault
    0.14
    rad
    0.14
    Act Density 0.003%

    No Known Activations