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

    Neuronpedia

    INDEX
    Explanations

    terms related to spans or spanning structures in a context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ,$_
    -0.69
     responseData
    -0.68
     Horace
    -0.66
     Alten
    -0.66
    👍🏻
    -0.64
     Weih
    -0.64
     Yahweh
    -0.63
     Dionys
    -0.61
    anima
    -0.60
     Rø
    -0.60
    POSITIVE LOGITS
     SPAN
    1.35
     spans
    1.34
     Span
    1.31
     span
    1.30
    spans
    1.24
    Span
    1.13
     spanned
    1.05
    espan
    1.03
    SPAN
    1.02
     spanning
    0.96
    Act Density 0.012%

    No Known Activations