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

    Neuronpedia

    INDEX
    Explanations

    expressions related to positive sentiment and support for social initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eraard
    -0.54
    verständlich
    -0.46
    choline
    -0.46
    Kelebihan
    -0.44
    tentu
    -0.44
     Rtl
    -0.42
     chi̍t
    -0.41
     gemeint
    -0.41
     према
    -0.41
    HORE
    -0.40
    POSITIVE LOGITS
     AssemblyTitle
    0.98
     kaarangay
    0.87
     pinulongan
    0.81
    expandindo
    0.77
     столь
    0.76
    sidemargin
    0.74
    如此
    0.71
     tão
    0.71
    TestingModule
    0.70
     چنین
    0.70
    Act Density 0.337%

    No Known Activations