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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbial phrases describing levels or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esub
    -0.18
    IBE
    -0.16
    ssi
    -0.16
    rary
    -0.15
    ellular
    -0.14
    istrat
    -0.14
    ucher
    -0.14
    rine
    -0.14
    onas
    -0.14
    noinspection
    -0.14
    POSITIVE LOGITS
    erre
    0.18
    ĮĴ
    0.15
    alls
    0.14
     å¾ĴæŃ©
    0.14
    821
    0.14
    Schedulers
    0.14
     Rah
    0.13
    zeitig
    0.13
    wards
    0.13
     miêu
    0.13
    Act Density 0.216%

    No Known Activations