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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo

    programming-related syntax and structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -1.04
    ento
    -0.80
    esis
    -0.73
    xon
    -0.72
    ulhu
    -0.71
    eteria
    -0.70
     Pearce
    -0.70
     Ago
    -0.68
    ertodd
    -0.65
    ciating
    -0.65
    POSITIVE LOGITS
    chance
    1.02
    taboola
    0.98
    dict
    0.91
    delay
    0.90
    bably
    0.89
    blank
    0.89
    train
    0.85
    due
    0.84
    default
    0.84
    self
    0.84
    Act Density 0.016%

    No Known Activations