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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "Any" is used before a statement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rex
    -0.78
    endas
    -0.77
    seless
    -0.72
    rea
    -0.70
    expensive
    -0.66
    romy
    -0.64
    itals
    -0.63
    alus
    -0.63
    ror
    -0.61
    rez
    -0.60
    POSITIVE LOGITS
    THING
    1.46
    WHERE
    1.12
     conceivable
    1.08
    body
    1.06
    where
    1.04
     semblance
    0.98
     imaginable
    0.96
    thin
    0.93
     kind
    0.92
    ONE
    0.90
    Act Density 0.826%

    No Known Activations