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

    Neuronpedia

    INDEX
    Explanations

    terms related to accreditation and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    849
    -0.16
    ÙĬج
    -0.15
    aking
    -0.15
    lp
    -0.15
    bum
    -0.15
    lfw
    -0.15
    iversal
    -0.14
    ltra
    -0.14
    lenen
    -0.14
    ioxide
    -0.14
    POSITIVE LOGITS
    idental
    0.30
    urate
    0.28
    idents
    0.28
    identally
    0.26
    redit
    0.24
    ident
    0.24
    ursed
    0.24
    IDENT
    0.23
    ueil
    0.23
    ustomed
    0.22
    Act Density 0.009%

    No Known Activations