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

    Neuronpedia

    INDEX
    Explanations

    terms related to gathering and presenting evidence or information

    oai_token-act-pair · gpt-3.5-turbo

    references to evidence, arguments, and the circulation of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itches
    -0.67
     renovated
    -0.67
    engeance
    -0.65
    ModLoader
    -0.64
     renovations
    -0.64
     renovation
    -0.62
     remod
    -0.61
    Measure
    -0.61
    digy
    -0.59
    Tok
    -0.59
    POSITIVE LOGITS
     uttered
    1.02
     glean
    1.02
     regarding
    0.99
     emanating
    0.88
     levied
    0.83
     hurled
    0.83
     Regarding
    0.81
     accumulated
    0.81
     concerning
    0.79
    andum
    0.76
    Act Density 0.447%

    No Known Activations