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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and actions

    oai_token-act-pair · gpt-3.5-turbo

    traditional customs or practices within a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )}
    -0.65
    aughtered
    -0.63
    ibles
    -0.62
    ITNESS
    -0.59
    itant
    -0.59
    ificantly
    -0.57
    FIG
    -0.57
    aband
    -0.56
    ificant
    -0.55
    amaz
    -0.55
    POSITIVE LOGITS
     hoping
    0.75
     inhib
    0.70
     allowing
    0.68
     claiming
    0.66
     expecting
    0.65
     whereby
    0.65
     gloom
    0.61
     fearing
    0.61
     creating
    0.61
     pretending
    0.60
    Act Density 1.121%

    No Known Activations