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

    Neuronpedia

    INDEX
    Explanations

    quantifiable comparisons and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.08
    openConnection
    -0.88
    DockStyle
    -0.83
    ThroughAttribute
    -0.77
    VolleyError
    -0.73
    enderror
    -0.70
    észetes
    -0.70
    AddTagHelper
    -0.67
     EconPapers
    -0.66
    bootstrapcdn
    -0.65
    POSITIVE LOGITS
     is
    0.74
     isComment
    0.56
     jesteśmy
    0.56
     really
    0.55
     isnt
    0.55
     are
    0.54
     Is
    0.51
     είναι
    0.50
     shouldBe
    0.49
    Siamo
    0.49
    Act Density 0.282%

    No Known Activations