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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters used in text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BufferException
    -0.46
     مشين
    -0.45
     MainAxisSize
    -0.43
     sztu
    -0.40
     saveiro
    -0.39
     ligiloj
    -0.38
    PYX
    -0.38
    )))),
    -0.37
    actéristi
    -0.37
     témoig
    -0.36
    POSITIVE LOGITS
    e
    0.99
    i
    0.79
    a
    0.78
    s
    0.78
    eis
    0.61
    t
    0.61
    o
    0.58
    ein
    0.56
    eli
    0.56
    ei
    0.56
    Act Density 0.665%

    No Known Activations