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

    Neuronpedia

    INDEX
    Explanations

    locations or directions indicated by the word "from."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "from" followed by numbers, typically indicating sources or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.67
    faced
    -0.67
    facts
    -0.66
    ortium
    -0.66
    quote
    -0.64
    grain
    -0.63
    itivity
    -0.63
    rite
    -0.62
    ratulations
    -0.60
    ema
    -0.60
    POSITIVE LOGITS
     afar
    1.52
     whence
    1.04
     abroad
    0.88
     atop
    0.84
     inside
    0.82
     behind
    0.81
     within
    0.80
     thence
    0.79
     wherever
    0.78
     upstairs
    0.77
    Act Density 0.126%

    No Known Activations