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

    Neuronpedia

    INDEX
    Explanations

    hyphenated terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "so-called" in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mock
    -0.69
     Mick
    -0.66
     Bryce
    -0.65
     ROCK
    -0.64
     Chop
    -0.63
     reservation
    -0.63
     Gorge
    -0.61
     Rivals
    -0.61
     attraction
    -0.61
     Illum
    -0.61
    POSITIVE LOGITS
    called
    1.63
    far
    1.16
    mentioned
    0.97
    named
    0.92
    often
    0.92
    shaped
    0.89
    known
    0.87
    sized
    0.85
    yet
    0.85
    described
    0.85
    Act Density 0.028%

    No Known Activations