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

    Neuronpedia

    INDEX
    Explanations

    verbs of decision-making or selection

    oai_token-act-pair · gpt-3.5-turbo

    short words with specific meanings or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.69
    adan
    -0.62
    Ļ½
    -0.62
     Poe
    -0.61
     Conce
    -0.59
    qua
    -0.58
    VERTISEMENT
    -0.58
    Ĭ±
    -0.58
    Center
    -0.58
    Ń·
    -0.57
    POSITIVE LOGITS
    ches
    1.35
    chers
    1.29
    tering
    1.22
    ters
    1.21
    tered
    1.16
    cher
    1.14
    ching
    1.13
    chy
    1.09
    hered
    1.09
    chet
    1.08
    Act Density 0.072%

    No Known Activations