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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the beginning of a new era or significant change

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the introduction of new concepts or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.75
    bia
    -0.72
    fts
    -0.72
    psons
    -0.69
     motive
    -0.67
    obbies
    -0.64
    ombies
    -0.63
    bite
    -0.62
    sol
    -0.61
    penter
    -0.61
    POSITIVE LOGITS
     usher
    1.11
     ushered
    0.95
    eers
    0.78
    wcs
    0.73
    inal
    0.72
    eering
    0.70
     inaug
    0.70
    glers
    0.70
    eer
    0.70
     celebrations
    0.68
    Act Density 0.020%

    No Known Activations