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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fill" in various grammatical forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.63
    GenerationType
    -0.61
    MessageOf
    -0.60
    UnusedPrivate
    -0.55
    FlatAppearance
    -0.55
    ViewFeatures
    -0.53
     surla
    -0.52
    IUrlHelper
    -0.52
    RegressionTest
    -0.52
    rrggbb
    -0.52
    POSITIVE LOGITS
    filling
    0.63
    Filling
    0.59
     gaps
    0.57
     filling
    0.55
     Gaps
    0.53
     Filling
    0.52
    fills
    0.49
     vacancies
    0.49
    Fill
    0.47
     FILL
    0.47
    Act Density 0.148%

    No Known Activations