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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and groups

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Democratic" and related mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.73
    rid
    -0.72
    imeter
    -0.69
    ifice
    -0.68
    atorium
    -0.68
    miss
    -0.66
    aste
    -0.65
    washer
    -0.65
    ust
    -0.64
    dule
    -0.64
    POSITIVE LOGITS
     who
    1.47
    who
    1.44
     whom
    1.35
     including
    1.22
     retirees
    1.11
     spouses
    1.09
    including
    1.01
     interns
    1.01
     educators
    1.00
     whose
    1.00
    Act Density 0.336%

    No Known Activations