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

    Neuronpedia

    INDEX
    Explanations

    instances indicating a need or requirement for something specific

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "a" followed by a noun or descriptor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESPN
    -0.74
    anism
    -0.69
    CI
    -0.69
    Arcade
    -0.66
    Assistant
    -0.65
    tm
    -0.65
    errors
    -0.64
    agree
    -0.63
    Ec
    -0.63
    aneously
    -0.63
    POSITIVE LOGITS
     lot
    1.09
    rouse
    0.95
     permanent
    0.95
     hefty
    0.93
     replacement
    0.92
     new
    0.92
     bunch
    0.91
     temporary
    0.90
     huge
    0.89
     definite
    0.88
    Act Density 0.413%

    No Known Activations