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

    Neuronpedia

    INDEX
    Explanations

    specific instances of the word "on" and its variations

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

    start/after 'on' is word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.65
     ſch
    -0.65
     ſtate
    -0.64
     ſte
    -0.61
     Autorizaciones
    -0.60
     ſta
    -0.59
    ésult
    -0.59
     houſe
    -0.57
    Cyfeiriadau
    -0.56
     Aze
    -0.54
    POSITIVE LOGITS
     been
    0.62
     è
    0.60
     είναι
    0.59
    是
    0.58
     ist
    0.58
     sont
    0.57
     ollut
    0.57
     is
    0.57
    ίναι
    0.56
     yra
    0.54
    Act Density 0.003%

    No Known Activations