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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "params" and related parameter terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pader
    -0.84
    
    -0.81
    circledR
    -0.78
    rsiniz
    -0.77
     Ender
    -0.73
    DeleteBehavior
    -0.73
    LookAnd
    -0.73
     Luch
    -0.72
    BufferException
    -0.72
     Bär
    -0.72
    POSITIVE LOGITS
    params
    2.40
     params
    2.31
    Params
    1.85
     Params
    1.60
    getParams
    1.37
    PARAMS
    1.29
     useParams
    0.97
    Param
    0.91
     param
    0.86
    param
    0.85
    Act Density 0.116%

    No Known Activations