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

    Neuronpedia

    INDEX
    Explanations

    political figures with their corresponding titles

    oai_token-act-pair · gpt-3.5-turbo

    references to political members and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caliphate
    -0.67
     traffickers
    -0.66
     Wrestle
    -0.66
     fulfillment
    -0.65
    istic
    -0.63
     primitive
    -0.62
     cue
    -0.61
     Provider
    -0.61
    tenance
    -0.61
     modernization
    -0.61
    POSITIVE LOGITS
    rieve
    1.15
    doms
    0.87
    aye
    0.84
    resent
    0.84
     voted
    0.83
     chairs
    0.83
     Dianne
    0.83
    hips
    0.79
    cill
    0.79
    rint
    0.79
    Act Density 0.101%

    No Known Activations