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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential outcomes, consequences, and predictions

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating future possibilities or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     burying
    -0.68
     praying
    -0.64
    kar
    -0.64
     submitting
    -0.64
     slaying
    -0.63
    arthed
    -0.63
     introducing
    -0.63
     Ivory
    -0.62
     preparing
    -0.62
     Serving
    -0.61
    POSITIVE LOGITS
     soar
    1.07
     vary
    1.07
     dwind
    1.07
     diminish
    1.05
     vanish
    1.04
     be
    1.02
     prevail
    1.02
     evapor
    1.01
     fluct
    1.01
     deterior
    1.00
    Act Density 0.188%

    No Known Activations