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

    Neuronpedia

    INDEX
    Explanations

    descriptions and assessments of various entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    genöss
    -0.47
    poň
    -0.45
     AssemblyTitle
    -0.43
    CloseOperation
    -0.43
     Cek
    -0.43
     him
    -0.42
    trup
    -0.40
    IntoConstraints
    -0.40
     dibat
    -0.40
     Hir
    -0.39
    POSITIVE LOGITS
     itself
    0.87
     cherchés
    0.74
    itself
    0.73
     surla
    0.71
    seamnă
    0.69
     himo
    0.69
    ⓧ
    0.66
    contentLoaded
    0.66
     Itself
    0.64
    ыгана
    0.62
    Act Density 0.583%

    No Known Activations