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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elly
    -0.18
    peria
    -0.15
    stk
    -0.15
    uni
    -0.14
    asts
    -0.14
     Malk
    -0.14
    asio
    -0.14
    каж
    -0.14
    ingu
    -0.13
     çŃ
    -0.13
    POSITIVE LOGITS
    idd
    0.16
    enco
    0.15
    neh
    0.15
    validated
    0.15
     Cruz
    0.14
     rev
    0.14
    IDD
    0.14
    chwitz
    0.14
    onne
    0.14
    nev
    0.14
    Act Density 0.166%

    No Known Activations