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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or logical connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tolsó
    -0.54
    inaison
    -0.51
     AssemblyCompany
    -0.47
     lisäksi
    -0.47
    __;
    -0.47
    glGen
    -0.46
    valently
    -0.44
     ModelExpression
    -0.44
    ENIA
    -0.43
    achable
    -0.43
    POSITIVE LOGITS
     etc
    2.04
    etc
    1.81
     Etc
    1.58
     usw
    1.50
    Etc
    1.44
     itp
    1.31
     sebagainya
    1.24
     ect
    1.22
     blah
    1.14
    之类的
    1.13
    Act Density 0.301%

    No Known Activations