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

    Neuronpedia

    INDEX
    Explanations

    specific references to systems, designs, or features that are tailored or intended for particular purposes or groups

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

    appearing before "designed" or "intended"

    np_acts-logits-general · gemini-2.0-flash

    specifically designed or intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueGenerated
    -0.67
     فريبيس
    -0.63
     betweenstory
    -0.62
     صوتيه
    -0.58
    dics
    -0.57
     stepfather
    -0.56
     onOptions
    -0.53
     disambiguazione
    -0.53
    říklad
    -0.51
     emu
    -0.50
    POSITIVE LOGITS
     designed
    2.17
     intended
    1.98
    designed
    1.82
     meant
    1.79
     Designed
    1.76
    intended
    1.72
    Designed
    1.66
    meant
    1.62
     Intended
    1.57
     предназна
    1.54
    Act Density 0.402%

    No Known Activations