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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to the level of certainty or visibility

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating a sense of obviousness or clarity about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -1.05
    alez
    -0.76
    yards
    -0.72
    gard
    -0.70
    dogs
    -0.69
    iership
    -0.68
    ests
    -0.67
     drilled
    -0.66
    ajo
    -0.65
     Hoy
    -0.65
    POSITIVE LOGITS
     contradictions
    1.10
     contradiction
    1.06
    iary
    0.91
     discrepancies
    0.88
     inconsistency
    0.84
     inability
    0.82
     inconsistencies
    0.78
     impossibility
    0.78
     resemblance
    0.78
     exception
    0.75
    Act Density 0.019%

    No Known Activations