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

    Neuronpedia

    INDEX
    Explanations

    terms related to model performance and limitations in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "is" or a form of "be"

    np_acts-logits-general · gemini-2.0-flash

    importance and validity of assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.70
     linkovi
    -0.69
    AppMethodBeat
    -0.64
    lccn
    -0.63
    исленность
    -0.63
     disambiguazione
    -0.60
     autorytatywna
    -0.60
    usermodel
    -0.59
     synced
    -0.59
     GenerationType
    -0.58
    POSITIVE LOGITS
     generali
    0.66
     critica
    0.61
     operacional
    0.59
     banques
    0.58
     generales
    0.58
     problèmes
    0.57
     potentially
    0.53
     phénomènes
    0.53
     procedimentos
    0.53
     typically
    0.52
    Act Density 2.093%

    No Known Activations