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

    Neuronpedia

    INDEX
    Explanations

    words related to substances and their variations

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

    substances: manufactured, called, active

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.58
    <unused41>
    -0.57
     nightmares
    -0.57
     Kühl
    -0.57
    <unused17>
    -0.56
    <unused16>
    -0.56
    <unused3>
    -0.56
    <unused28>
    -0.56
    [@BOS@]
    -0.56
    <pad>
    -0.56
    POSITIVE LOGITS
     substances
    1.16
     substance
    1.14
     Substance
    0.97
    substance
    0.95
    Substance
    0.94
     Substances
    0.93
     sustancia
    0.92
     sustancias
    0.90
     sostanza
    0.88
     sostanze
    0.87
    Act Density 0.007%

    No Known Activations