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

    Neuronpedia

    INDEX
    Explanations

    references to ongoing issues or events

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing events or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingers
    -0.92
    yp
    -0.79
    ique
    -0.78
    oak
    -0.77
    pper
    -0.76
    ppers
    -0.76
    acked
    -0.75
    imble
    -0.75
    otle
    -0.74
    fing
    -0.74
    POSITIVE LOGITS
     developments
    1.01
     ongoing
    1.00
     hostilities
    0.90
     upkeep
    0.86
     investigations
    0.84
     saga
    0.84
     unresolved
    0.84
     tense
    0.82
     efforts
    0.81
     discussions
    0.77
    Act Density 0.017%

    No Known Activations