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

    Neuronpedia

    INDEX
    Explanations

    steps and sequences in procedural instructions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Pende
    -0.66
     ſeveral
    -0.64
     ―――――
    -0.63
     itſelf
    -0.63
     Theſe
    -0.61
     Reſ
    -0.60
    Segue
    -0.60
     sumpay
    -0.60
     ſtand
    -0.59
    VersionUID
    -0.59
    POSITIVE LOGITS
    Obras
    0.54
     $
    0.52
     AssemblyCompany
    0.50
    Parcel
    0.47
     kér
    0.46
    intellij
    0.45
    expire
    0.44
     فريبيس
    0.43
    WAUKEE
    0.43
    protoc
    0.43
    Act Density 0.001%

    No Known Activations