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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the word "as" in various contexts

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

    as part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pihaknya
    -0.36
    onInit
    -0.36
     lähe
    -0.35
     fondateur
    -0.34
     followed
    -0.34
     peuple
    -0.34
     hace
    -0.33
     Bupati
    -0.33
     commandement
    -0.32
     võ
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.76
    IsContent
    0.69
     nakalista
    0.65
     pinulongan
    0.64
    parsedMessage
    0.62
    <unused41>
    0.60
    <unused14>
    0.60
    extAlignment
    0.60
    <unused28>
    0.60
    <unused47>
    0.60
    Act Density 0.063%

    No Known Activations