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

    Neuronpedia

    INDEX
    Explanations

    words related to physical states of imbalance or distress

    oai_token-act-pair · gpt-3.5-turbo

    non-standard spelling or linguistic oddities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bnb
    -0.74
    çīĪ
    -0.67
     sclerosis
    -0.67
    ãĥī
    -0.66
    terday
    -0.66
    etheus
    -0.64
    peria
    -0.64
    代
    -0.64
    ricanes
    -0.64
    ample
    -0.63
    POSITIVE LOGITS
    ered
    1.48
    ering
    1.39
    ers
    1.26
    ery
    1.05
    erers
    1.04
    ern
    1.04
    erer
    1.02
    ellery
    1.01
    eling
    1.00
    ership
    1.00
    Act Density 0.025%

    No Known Activations