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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    historical references or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minimum
    -0.68
    een
    -0.68
     Alic
    -0.65
    shr
    -0.64
    uti
    -0.63
    cakes
    -0.63
     advoc
    -0.63
    estyles
    -0.62
    specific
    -0.62
    ãĤ¢ãĥ«
    -0.61
    POSITIVE LOGITS
    oat
    0.70
    avascript
    0.61
    oqu
    0.61
    otion
    0.60
    lyak
    0.59
     dilemma
    0.58
    unction
    0.58
    hetamine
    0.57
    ogging
    0.57
    ication
    0.57
    Act Density 0.000%

    No Known Activations