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

    Neuronpedia

    INDEX
    Explanations

    words that convey certainty or emphasis on consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Undef
    -0.17
    achsen
    -0.15
    zew
    -0.15
    recated
    -0.14
    .sul
    -0.14
    rij
    -0.14
    uitka
    -0.14
    ạm
    -0.14
    LOAT
    -0.14
    lesh
    -0.14
    POSITIVE LOGITS
     trust
    0.15
     sebou
    0.14
     pers
    0.14
    åľ
    0.14
     perfect
    0.14
    cky
    0.13
    itsu
    0.13
    arkin
    0.13
     truths
    0.13
     Maintenance
    0.13
    Act Density 0.007%

    No Known Activations