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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures, specifically Abraham Lincoln

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ttes
    -0.81
    nces
    -0.79
    essee
    -0.78
    prus
    -0.74
    agra
    -0.70
    hift
    -0.66
    TOP
    -0.66
     Flavoring
    -0.66
    Downloadha
    -0.64
     Sahara
    -0.63
    POSITIVE LOGITS
    raham
    1.10
    son
    1.04
     Lincoln
    0.99
    sen
    0.91
    sson
    0.85
    sburg
    0.84
    antine
    0.81
    shire
    0.81
    ode
    0.80
     Abram
    0.79
    Act Density 0.027%

    No Known Activations