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

    Neuronpedia

    INDEX
    Explanations

    tentative affirmations and expressions of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RTLD
    -0.52
     مشين
    -0.46
    ryn
    -0.44
    UnusedPrivate
    -0.43
     Bench
    -0.42
    comune
    -0.42
    Prak
    -0.42
    Personendaten
    -0.41
     Democrá
    -0.41
    brush
    -0.41
    POSITIVE LOGITS
     säkert
    0.58
     assuredly
    0.50
     seguramente
    0.49
    OGND
    0.48
     doubtless
    0.48
     hopefully
    0.47
    andExpect
    0.47
    oubtedly
    0.46
    assertNotNull
    0.46
    想必
    0.45
    Act Density 0.272%

    No Known Activations