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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating improvement or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clearfix
    -0.36
    спубли
    -0.35
    ower
    -0.33
    arro
    -0.32
     Schna
    -0.32
     κ
    -0.31
    брать
    -0.31
    裝
    -0.31
     μου
    -0.31
    onnes
    -0.30
    POSITIVE LOGITS
     resourceCulture
    1.12
     AssemblyCulture
    1.08
    Tikang
    1.04
     للمعارف
    1.04
     يتيمه
    1.03
     kasarigan
    1.01
     متعلقه
    1.00
    WriteTagHelper
    0.99
    tagHelperRunner
    0.97
    WithIOException
    0.96
    Act Density 0.140%

    No Known Activations