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

    Neuronpedia

    INDEX
    Explanations

    words related to physical states like smoothness, consistency, and uniformity

    oai_token-act-pair · gpt-3.5-turbo

    words and suffixes related to qualities or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergy
    -0.67
    inav
    -0.62
    iverse
    -0.61
    ERC
    -0.60
     Vid
    -0.60
    awar
    -0.59
     Bed
    -0.58
     Wake
    -0.58
    LOCK
    -0.57
     Mast
    -0.57
    POSITIVE LOGITS
    iness
    1.16
    ously
    0.93
    iveness
    0.84
     Flavoring
    0.80
    icity
    0.79
    worthiness
    0.77
     quot
    0.77
    ionage
    0.75
    lessness
    0.75
    fulness
    0.74
    Act Density 0.081%

    No Known Activations