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

    Neuronpedia

    INDEX
    Explanations

    contractions of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Courier
    -0.15
    gnore
    -0.15
    ajs
    -0.14
    _dp
    -0.14
    ombat
    -0.14
    vars
    -0.14
    YNAMIC
    -0.14
    dp
    -0.14
    ictionaries
    -0.13
    Ñĸп
    -0.13
    POSITIVE LOGITS
    #ad
    0.16
    ãĥ«ãĥķ
    0.15
    haar
    0.14
    OutOfRangeException
    0.14
    erer
    0.14
    allis
    0.14
    appers
    0.14
     gonna
    0.14
    @nate
    0.14
    errar
    0.13
    Act Density 0.049%

    No Known Activations