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

    Neuronpedia

    INDEX
    Explanations

    instances of introductory phrases and transitional words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.83
    MemoryWarning
    -0.75
    ^(@)
    -0.74
    EndInit
    -0.70
    новниш
    -0.70
    Sklici
    -0.69
     BoxDecoration
    -0.69
     تانيه
    -0.68
    ToScroll
    -0.67
    spesies
    -0.67
    POSITIVE LOGITS
    ↵↵
    0.51
    (
    0.46
    stubs
    0.46
    ↵
    0.45
     pourrais
    0.44
    ऋ
    0.43
    ությ
    0.43
    openzeppelin
    0.41
    домо
    0.41
     such
    0.39
    Act Density 0.895%

    No Known Activations