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

    Neuronpedia

    INDEX
    Explanations

    references to various news events and controversies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the indefinite articles "a" and "an"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.83
    grounds
    -0.83
    ographs
    -0.83
    coins
    -0.80
    marks
    -0.79
    eyes
    -0.78
    Examples
    -0.76
    stars
    -0.76
    cells
    -0.75
    apps
    -0.74
    POSITIVE LOGITS
     slew
    1.08
     nonexistent
    1.06
     plethora
    1.05
     forthcoming
    1.04
     longstanding
    1.04
     burgeoning
    0.99
     multitude
    0.96
    usterity
    0.96
     hypothetical
    0.96
     mythical
    0.94
    Act Density 0.454%

    No Known Activations