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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and words indicating uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æģĴ
    -0.18
    mile
    -0.17
    ritz
    -0.16
    enson
    -0.16
    uji
    -0.16
    ãĥ
    -0.15
    phere
    -0.15
    andler
    -0.15
     Feinstein
    -0.15
    orie
    -0.15
    POSITIVE LOGITS
    aket
    0.15
    FieldValue
    0.15
    aqu
    0.15
    ada
    0.14
    adi
    0.14
    ush
    0.14
    atto
    0.14
    aksi
    0.14
    yre
    0.14
     subs
    0.14
    Act Density 0.480%

    No Known Activations