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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to physical attributes of objects or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize conjunctions and connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enth
    -0.83
    uda
    -0.80
    adow
    -0.79
    queue
    -0.79
    aez
    -0.78
    matter
    -0.78
    wark
    -0.77
    oti
    -0.75
    ãĤ¨ãĥ«
    -0.75
    opol
    -0.74
    POSITIVE LOGITS
     ample
    1.13
     abundant
    1.12
     hefty
    1.12
     generous
    1.10
     penchant
    1.10
     impecc
    1.09
     unparalleled
    1.08
     extensive
    1.06
     scant
    1.06
     plentiful
    1.04
    Act Density 0.358%

    No Known Activations