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

    Neuronpedia

    INDEX
    Explanations

    the word "any" occurring multiple times in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "any."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endas
    -0.76
    rex
    -0.72
    combe
    -0.72
    rez
    -0.68
    rea
    -0.67
    staking
    -0.66
    appings
    -0.65
    icz
    -0.65
    ributes
    -0.65
    itz
    -0.65
    POSITIVE LOGITS
    THING
    1.30
     conceivable
    1.10
    WHERE
    1.08
     imaginable
    1.06
    where
    1.03
    ONE
    1.02
    body
    1.02
     kind
    0.93
     sort
    0.91
    thin
    0.87
    Act Density 0.070%

    No Known Activations