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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to political organizations or events

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular political conference or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goo
    -0.74
    tainment
    -0.72
    prises
    -0.70
     Admir
    -0.70
    wagen
    -0.69
    sbm
    -0.69
    ebted
    -0.65
    cknowled
    -0.63
    âĸ¬
    -0.63
    utm
    -0.62
    POSITIVE LOGITS
    ython
    0.92
    erity
    0.92
    ople
    0.91
    VC
    0.88
    illon
    0.86
    PLA
    0.86
    AN
    0.85
    enhagen
    0.85
    ocalypse
    0.84
    TPP
    0.84
    Act Density 0.019%

    No Known Activations