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

    Neuronpedia

    INDEX
    Explanations

    words related to units of data size

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "ter"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELS
    -0.77
    orship
    -0.75
    Downloadha
    -0.70
    UME
    -0.70
    issance
    -0.69
    OWS
    -0.66
    hetti
    -0.65
    éĹĺ
    -0.63
    etts
    -0.63
    ा
    -0.62
    POSITIVE LOGITS
    abytes
    1.18
    rible
    1.14
    rors
    1.09
    rier
    1.08
    ranean
    1.07
    riers
    1.05
    abyte
    1.04
    mination
    1.01
    mine
    1.01
    race
    1.00
    Act Density 0.013%

    No Known Activations