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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a recurring pattern or action happening consecutively

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in a row" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.78
     streng
    -0.73
    milo
    -0.68
    inav
    -0.68
    onom
    -0.67
    ãĥ¤
    -0.66
     Zeit
    -0.64
    obin
    -0.63
    amina
    -0.62
    roots
    -0.62
    POSITIVE LOGITS
     ..........
    0.71
    dies
    0.71
    Fla
    0.71
     ago
    0.70
    VERT
    0.67
    dy
    0.67
    nd
    0.66
    DOWN
    0.64
    FTWARE
    0.61
    --------------------------------------------------------
    0.61
    Act Density 0.013%

    No Known Activations