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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or developments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     prefers
    -0.72
     liking
    -0.71
    responsive
    -0.68
     consulted
    -0.66
     preferring
    -0.66
     motions
    -0.64
     Recommended
    -0.64
     behaves
    -0.60
     neglig
    -0.60
     crawling
    -0.60
    POSITIVE LOGITS
    ¿½
    0.79
    wcs
    0.78
     precedent
    0.78
     renewed
    0.74
     momentum
    0.72
    orsche
    0.72
     morale
    0.71
     bitters
    0.71
    amsung
    0.71
    ibaba
    0.70
    Act Density 0.648%

    No Known Activations