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

    Neuronpedia

    INDEX
    Explanations

    references to the term "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.87
    MLLoader
    -0.70
    DebuggerNonUser
    -0.69
    OGND
    -0.67
     houſe
    -0.66
     purpoſe
    -0.65
     οποία
    -0.64
     ModelExpression
    -0.63
    horabuena
    -0.63
     <=",
    -0.62
    POSITIVE LOGITS
     a
    0.71
     as
    0.70
     ως
    0.62
    ujud
    0.61
    jako
    0.59
    成
    0.59
     sebagai
    0.59
    readAs
    0.58
    essment
    0.58
    ivably
    0.57
    Act Density 0.221%

    No Known Activations