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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics and news

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.75
    _.
    -0.71
    CONCLUS
    -0.70
    States
    -0.66
    tics
    -0.66
     destro
    -0.64
    6000
    -0.63
     smugglers
    -0.63
    Closure
    -0.62
    MU
    -0.62
    POSITIVE LOGITS
     embattled
    0.78
     Donald
    0.68
     superstar
    0.63
    dinand
    0.61
     Antonio
    0.60
     John
    0.60
     Adolf
    0.60
     iconic
    0.59
     Tim
    0.58
     ...
    0.57
    Act Density 0.283%

    No Known Activations