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

    Neuronpedia

    INDEX
    Explanations

    keyword pairs signaling critical or intense situations

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onom
    -0.71
     Redmond
    -0.67
    Polit
    -0.64
    atorium
    -0.64
    ËĪ
    -0.62
     Bern
    -0.62
     Pog
    -0.61
     Roose
    -0.60
     Malaysia
    -0.59
    itialized
    -0.58
    POSITIVE LOGITS
    anwhile
    0.95
     respectively
    0.86
     thereby
    0.84
    entimes
    0.79
     furthermore
    0.78
    ogether
    0.72
    thus
    0.71
     culmin
    0.70
     convol
    0.70
     culminated
    0.70
    Act Density 1.287%

    No Known Activations