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

    Neuronpedia

    INDEX
    Explanations

    percentages and monetary values in text related to systems or evaluations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.90
     resourceCulture
    -0.82
    nościo
    -0.82
    ReusableCell
    -0.69
    ValueGeneration
    -0.68
    énario
    -0.67
    
    -0.65
    LinkId
    -0.63
    脚注の使い方
    -0.60
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
    født
    0.58
    OGND
    0.55
     szóci
    0.50
     lau
    0.47
    ?»
    0.45
    تقاوى
    0.45
     Meksiku
    0.44
    ++]=
    0.44
    !»
    0.43
    /$',
    0.43
    Act Density 0.606%

    No Known Activations