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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality and results

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or effects related to specific results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.85
    horn
    -0.77
    ppa
    -0.77
    ario
    -0.70
    irens
    -0.69
    lest
    -0.68
    quet
    -0.67
    asive
    -0.66
    Daddy
    -0.66
    eers
    -0.66
    POSITIVE LOGITS
     sheer
    0.77
     inaction
    0.71
     undergoing
    0.69
     lying
    0.67
     circumstance
    0.66
     Antar
    0.66
     shelling
    0.66
     rounding
    0.66
     absorbing
    0.66
     pree
    0.65
    Act Density 0.067%

    No Known Activations