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

    Neuronpedia

    INDEX
    Explanations

    generic versatile terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "any" and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illard
    -0.78
    alus
    -0.75
    mand
    -0.71
    BA
    -0.70
    pee
    -0.70
    pu
    -0.69
    ba
    -0.68
    FH
    -0.67
    tails
    -0.66
    irth
    -0.65
    POSITIVE LOGITS
     imaginable
    1.36
     conceivable
    1.05
    THING
    1.03
    where
    0.98
     else
    0.93
     kind
    0.86
    body
    0.84
     sort
    0.84
    Else
    0.81
     sorts
    0.80
    Act Density 0.076%

    No Known Activations