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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or doubt in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Viitteet
    -0.51
     nakalista
    -0.49
     Traducción
    -0.48
     Biôgrafia
    -0.47
    ply
    -0.47
     biasa
    -0.47
    책
    -0.46
    urgo
    -0.45
     lourdes
    -0.45
    DTD
    -0.45
    POSITIVE LOGITS
     neither
    1.39
    neither
    1.29
     tampoco
    1.26
     Tampoco
    1.17
    Neither
    1.15
     nor
    1.14
     Neither
    1.10
    nor
    1.00
    Nor
    0.99
     Nor
    0.98
    Act Density 0.253%

    No Known Activations