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

    Neuronpedia

    INDEX
    Explanations

    the frequency of prepositions and conjunctions in the text

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

    beginning in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.65
    IUrlHelper
    -0.59
     ſch
    -0.57
    AutoScaleMode
    -0.56
    Personensuche
    -0.56
    Datuak
    -0.54
    Filmographie
    -0.53
     насељу
    -0.53
    schild
    -0.52
     Италијани
    -0.51
    POSITIVE LOGITS
     early
    0.50
     during
    0.47
     the
    0.42
     inaugural
    0.42
     late
    0.41
     afternoon
    0.41
     initial
    0.41
     Friday
    0.41
     opening
    0.41
     half
    0.40
    Act Density 0.022%

    No Known Activations