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

    Neuronpedia

    INDEX
    Explanations

    instances where the characters 'Ċ' and 'Ŀ' appear

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant numbers or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unin
    -0.70
     inactive
    -0.70
     endeav
    -0.67
     precaution
    -0.67
     stray
    -0.65
     active
    -0.65
     honoured
    -0.64
     manoeuv
    -0.64
     Reincarnated
    -0.64
     endeavour
    -0.63
    POSITIVE LOGITS
    ³³³³
    1.02
    ³³³
    0.94
    ³³³³³³³³
    0.91
    ³³
    0.87
    ³³³³³³³³³³³³³³³³
    0.87
    Loading
    0.87
    posted
    0.87
    ccording
    0.86
    =-=-=-=-=-=-=-=-
    0.83
    Anonymous
    0.82
    Act Density 0.165%

    No Known Activations