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

    Neuronpedia

    INDEX
    Explanations

    unclear or ambiguous statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or clarity regarding events or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sacrific
    -0.77
     greatness
    -0.69
     wanna
    -0.66
     Ancients
    -0.65
    luaj
    -0.64
    die
    -0.64
     Preferences
    -0.62
     mastery
    -0.62
     Chosen
    -0.62
     majesty
    -0.61
    POSITIVE LOGITS
     unclear
    1.29
     unlikely
    0.88
    enhagen
    0.84
     also
    0.82
     speculated
    0.79
     unsur
    0.78
     additionally
    0.77
     prompted
    0.76
     ironic
    0.75
     reportedly
    0.75
    Act Density 0.329%

    No Known Activations