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

    Neuronpedia

    INDEX
    Explanations

    instructions and warnings related to food safety

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

    Followed by punctuation or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    advise women; contraindications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.59
     it
    -0.59
    ,
    -0.57
     you
    -0.54
     -
    -0.54
     
    -0.54
     i
    -0.53
     –
    -0.52
     is
    -0.52
     just
    -0.52
    POSITIVE LOGITS
     ་་
    0.95
     itſelf
    0.92
     myſelf
    0.91
     Majefty
    0.91
     Moslem
    0.90
     Jefus
    0.90
     pleaſure
    0.89
    ſelf
    0.88
     ―――――
    0.87
     greateſt
    0.86
    Act Density 0.270%

    No Known Activations