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

    Neuronpedia

    INDEX
    Explanations

    medical expertise and references to healthcare professionals

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

    Follows "to" or certain punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    older english and french influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pretty
    -0.74
     clueless
    -0.69
     supposedly
    -0.68
     
    -0.64
     actually
    -0.63
     messed
    -0.63
     weirdly
    -0.63
     вроде
    -0.63
     tricky
    -0.62
     T
    -0.62
    POSITIVE LOGITS
     itſelf
    1.02
     myſelf
    0.98
     ainfi
    0.95
     Monfieur
    0.94
     ་་
    0.94
     pleaſure
    0.92
     auffi
    0.92
    ſelves
    0.91
     enfans
    0.89
     purpoſe
    0.89
    Act Density 0.258%

    No Known Activations