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

    Neuronpedia

    INDEX
    Explanations

    occurrences of introductory phrases and common conjunctions

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

    Starting a sentence with "In"

    np_acts-logits-general · gemini-2.0-flash

    "in" followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.90
    -0.88
    ValueStyle
    -0.78
     ་་
    -0.78
    <unused74>
    -0.77
    <unused14>
    -0.77
    <unused41>
    -0.77
    <unused42>
    -0.77
    <unused8>
    -0.77
    [@BOS@]
    -0.77
    POSITIVE LOGITS
    In
    0.83
     In
    0.82
    As
    0.54
     As
    0.51
    For
    0.51
    At
    0.48
     For
    0.47
     At
    0.47
    On
    0.46
     În
    0.45
    Act Density 0.547%

    No Known Activations