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

    Neuronpedia

    INDEX
    Explanations

    the word "any"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "any" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rex
    -0.77
    seless
    -0.74
    rez
    -0.70
    expensive
    -0.68
    bows
    -0.65
    ros
    -0.65
    endas
    -0.64
    appings
    -0.63
    agos
    -0.62
    iano
    -0.60
    POSITIVE LOGITS
    THING
    1.36
    body
    0.97
    WHERE
    0.96
    where
    0.94
    thin
    0.91
     conceivable
    0.90
    ONE
    0.89
     else
    0.80
     other
    0.78
     imaginable
    0.74
    Act Density 0.077%

    No Known Activations