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

    Neuronpedia

    INDEX
    Explanations

    words related to social issues and political discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.79
    hyde
    -0.75
    starting
    -0.72
    roller
    -0.70
    wagon
    -0.68
    rolling
    -0.66
    apt
    -0.65
    NEY
    -0.64
    upon
    -0.63
    lees
    -0.63
    POSITIVE LOGITS
    ebin
    1.66
     decade
    1.27
     tense
    1.08
     week
    0.99
     generations
    0.99
     few
    0.98
     month
    0.97
     millennium
    0.96
     decades
    0.95
     fortnight
    0.94
    Act Density 0.783%

    No Known Activations