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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mental attitude and productivity

    oai_token-act-pair · gpt-3.5-turbo

    coordinating conjunctions and repeated phrases indicating continuity or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.77
     ®
    -0.70
    zu
    -0.65
    apor
    -0.65
    hered
    -0.63
    !:
    -0.63
    antine
    -0.61
    ãĥĭ
    -0.61
    iren
    -0.59
    successfully
    -0.57
    POSITIVE LOGITS
     blah
    1.14
     stuff
    1.10
     everybody
    1.04
    romeda
    1.02
     yeah
    0.97
     maybe
    0.93
     secondly
    0.93
     hopefully
    0.92
     frankly
    0.90
     somebody
    0.88
    Act Density 0.323%

    No Known Activations