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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a sense of uncertainty or vagueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oídos
    -0.55
     rač
    -0.54
     vettoriale
    -0.51
     vermelhas
    -0.51
     finanzas
    -0.50
    VIAF
    -0.50
     extinción
    -0.49
     Füßen
    -0.49
     hlavy
    -0.49
     kaikki
    -0.48
    POSITIVE LOGITS
     something
    1.61
    something
    1.48
    Something
    1.48
     Something
    1.43
     SOMETHING
    1.30
     someone
    1.23
     somethin
    1.23
    someone
    1.20
    Someone
    1.16
     somewhere
    1.13
    Act Density 0.092%

    No Known Activations