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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "obligation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wyn
    -0.16
    HWND
    -0.15
     Sick
    -0.15
    MING
    -0.15
    onces
    -0.14
    zung
    -0.14
    asters
    -0.14
    اØŃت
    -0.14
    <Props
    -0.14
    egasus
    -0.14
    POSITIVE LOGITS
    lique
    0.31
     ob
    0.24
    noxious
    0.24
    liqu
    0.23
    sequ
    0.22
    fuscated
    0.22
    VIOUS
    0.22
     Ob
    0.21
    fusc
    0.21
    serve
    0.20
    Act Density 0.009%

    No Known Activations