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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "On."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     in
    -0.57
    ToUse
    -0.57
    اً
    -0.56
     The
    -0.54
    ://"
    -0.54
     the
    -0.51
     "
    -0.50
     In
    -0.50
     a
    -0.48
     addition
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.84
     OkHttpClient
    0.82
    ValueStyle
    0.81
    Джерела
    0.78
    extAlignment
    0.78
     lenker
    0.77
     AssemblyCompany
    0.76
    tvguidetime
    0.76
    SharedCtor
    0.76
     שוליים
    0.75
    Act Density 0.026%

    No Known Activations