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

    Neuronpedia

    INDEX
    Explanations

    discussions about the effects and impacts of various factors in research studies

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

    effect ofrelationship between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.40
     насеље
    -0.33
    impianto
    -0.32
    insegna
    -0.31
    แน
    -0.30
     Krueger
    -0.30
     fab
    -0.30
     pezzo
    -0.30
     národ
    -0.28
     Democrá
    -0.28
    POSITIVE LOGITS
    AndEndTag
    0.68
    <unused41>
    0.64
    <unused8>
    0.64
    [@BOS@]
    0.64
    <unused14>
    0.64
    <unused51>
    0.64
    <unused3>
    0.64
    <unused74>
    0.64
    <unused1>
    0.63
    <unused17>
    0.63
    Act Density 0.370%

    No Known Activations