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

    Neuronpedia

    INDEX
    Explanations

    singular words that convey affirmation or positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swer
    -0.18
    itler
    -0.17
    iche
    -0.15
    URITY
    -0.14
    astle
    -0.14
    akens
    -0.14
    pras
    -0.14
    ίοÏĤ
    -0.14
    itionally
    -0.14
     κοι
    -0.14
    POSITIVE LOGITS
    oya
    0.18
    lags
    0.15
    ach
    0.14
    aint
    0.14
    nofollow
    0.14
    erness
    0.14
    nth
    0.14
    inas
    0.14
    osh
    0.13
     @@↵
    0.13
    Act Density 0.245%

    No Known Activations