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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the number 'three'

    oai_token-act-pair · gpt-3.5-turbo

    references to the number three

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IAS
    -0.67
     srf
    -0.64
    UGE
    -0.64
    agate
    -0.63
    isky
    -0.60
    byss
    -0.57
    ULE
    -0.57
    ITH
    -0.57
    stakes
    -0.56
    staking
    -0.56
    POSITIVE LOGITS
    rd
    1.29
    teenth
    1.22
    peat
    1.07
    teen
    1.07
     quarters
    1.06
     hundred
    0.99
    uously
    0.97
    fold
    0.95
     dimensional
    0.94
    quel
    0.92
    Act Density 0.066%

    No Known Activations