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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seless
    -0.77
    rex
    -0.72
    plex
    -0.69
    staking
    -0.67
    ancouver
    -0.66
    yrinth
    -0.65
    ward
    -0.63
    gal
    -0.63
    Bee
    -0.62
    visor
    -0.61
    POSITIVE LOGITS
    THING
    1.28
    ones
    0.95
     longer
    0.89
    WHERE
    0.89
     particular
    0.88
    ONE
    0.88
    place
    0.85
     significant
    0.85
     other
    0.83
     meaningful
    0.83
    Act Density 0.063%

    No Known Activations