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

    Neuronpedia

    INDEX
    Explanations

    the word "any" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "any."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seless
    -0.77
    rex
    -0.74
    plex
    -0.73
    rox
    -0.68
    ip
    -0.67
    gal
    -0.66
    ulo
    -0.66
    grad
    -0.64
    yrinth
    -0.64
    itals
    -0.64
    POSITIVE LOGITS
    THING
    1.30
    WHERE
    1.04
     significant
    0.91
     meaningful
    0.88
    place
    0.86
     particular
    0.84
    ONE
    0.83
     additional
    0.82
     longer
    0.81
    ones
    0.80
    Act Density 0.066%

    No Known Activations