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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
     ""),
    -0.70
    ".$
    -0.69
     "")
    -0.68
    '";
    -0.67
    '=>$
    -0.66
    '.$
    -0.66
    marle
    -0.65
     ?";
    -0.65
    <?
    -0.64
    POSITIVE LOGITS
     estekak
    0.69
    BufferException
    0.66
    例句
    0.66
     mourut
    0.66
    helves
    0.65
     Secara
    0.64
    ImageContext
    0.62
     odkazy
    0.61
     gynhyrchwyd
    0.61
    Hochspringen
    0.58
    Act Density 0.170%

    No Known Activations