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

    Neuronpedia

    INDEX
    Explanations

    substrings starting with "sub-"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "sub."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OHN
    -0.89
    ILLE
    -0.82
    IELD
    -0.76
    ESCO
    -0.76
     Qiao
    -0.73
    ORED
    -0.73
     Zurich
    -0.72
     Lauder
    -0.72
    Ö¼
    -0.71
    FORE
    -0.71
    POSITIVE LOGITS
    missive
    1.26
    mitter
    1.21
    verting
    1.15
    mitted
    1.12
    sequent
    1.09
    species
    1.09
    sequently
    1.07
    miss
    1.04
    missible
    1.02
    ordinate
    1.01
    Act Density 0.012%

    No Known Activations