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

    Neuronpedia

    INDEX
    Explanations

    the preposition "in" across various contexts

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

    prepositional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.82
     المعيارى
    -0.81
     ddelwed
    -0.80
     Monfieur
    -0.80
     Verſ
    -0.79
    <unused74>
    -0.78
    <unused80>
    -0.78
    <unused41>
    -0.77
    <unused28>
    -0.77
    <unused8>
    -0.77
    POSITIVE LOGITS
     during
    0.38
     despite
    0.37
     without
    0.36
     as
    0.35
     while
    0.34
     kesan
    0.33
     olacaktır
    0.33
     which
    0.33
     samtidig
    0.33
     if
    0.32
    Act Density 0.209%

    No Known Activations