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

    Neuronpedia

    INDEX
    Explanations

    words/phrases indicating an alternative choice or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "instead" highlighting alternatives or substitutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ankind
    -0.67
    andestine
    -0.64
    vez
    -0.62
    ced
    -0.58
    IENT
    -0.57
    beans
    -0.55
    estern
    -0.54
    nce
    -0.54
    ESE
    -0.54
    Interstitial
    -0.54
    POSITIVE LOGITS
     thereof
    0.90
     opting
    0.84
     of
    0.80
    paces
    0.71
     preferring
    0.69
    liga
    0.69
    ilon
    0.68
    falls
    0.68
    of
    0.67
    pling
    0.67
    Act Density 0.027%

    No Known Activations