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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
    "}")
    -0.54
    Gente
    -0.52
    </b>
    -0.51
    uke
    -0.50
    '}';
    -0.50
    '];?>
    -0.50
    "}"
    -0.50
     combination
    -0.48
    zit
    -0.48
    POSITIVE LOGITS
     as
    1.16
     AssemblyCulture
    1.03
     CreateTagHelper
    0.98
     Normdatei
    0.84
     صوتيه
    0.80
    InjectAttribute
    0.78
     As
    0.78
    ItemBackground
    0.75
     وتسجيلات
    0.74
    unmodifiable
    0.73
    Act Density 0.234%

    No Known Activations