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

    Neuronpedia

    INDEX
    Explanations

    specific suffixes and grammatical markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gro
    -0.17
    izr
    -0.16
     par
    -0.16
    baz
    -0.16
    ABCDE
    -0.15
    gend
    -0.15
    forum
    -0.15
    Incomplete
    -0.15
     MK
    -0.15
    abi
    -0.14
    POSITIVE LOGITS
    pest
    0.18
    idge
    0.18
    ãĥĥ
    0.18
    owler
    0.16
    wall
    0.16
     t
    0.16
    çļ®
    0.16
    mo
    0.15
     Berger
    0.14
    _EC
    0.14
    Act Density 0.045%

    No Known Activations