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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing obligation or recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.88
     mData
    -0.85
     Efq
    -0.81
     Comer
    -0.74
     langt
    -0.73
    PyExc
    -0.73
     BoxDecoration
    -0.71
     geçmiş
    -0.71
     mxArray
    -0.71
     ujednoznacz
    -0.71
    POSITIVE LOGITS
     should
    1.51
     SHOULD
    1.42
    hould
    1.35
     Should
    1.35
    should
    1.21
    Should
    1.15
     be
    1.11
     shouldn
    1.02
     ought
    1.02
     devriez
    0.95
    Act Density 0.090%

    No Known Activations