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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

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

    on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.53
    Personendaten
    -0.48
    -------
    -0.48
    InteropServices
    -0.46
    مراجع
    -0.45
    Referencies
    -0.39
    gsmål
    -0.39
    aarrggbb
    -0.39
     Normdatei
    -0.38
     cuidadosamente
    -0.37
    POSITIVE LOGITS
     ON
    0.55
     onward
    0.54
     onto
    0.52
    IntoConstraints
    0.49
     onwards
    0.49
     on
    0.49
     onBind
    0.48
    banners
    0.47
     Ont
    0.47
     weekdays
    0.47
    Act Density 0.041%

    No Known Activations