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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -1.12
    <eos>
    -1.09
    ↵
    -0.95
    ,
    -0.95
     
    -0.92
    ?
    -0.82
      
    -0.82
    ’
    -0.79
     of
    -0.79
    ;
    -0.78
    POSITIVE LOGITS
     ―――――
    1.29
     ་་
    1.26
     itſelf
    1.24
     myſelf
    1.18
     doubtnut
    1.09
    ſelves
    1.07
    NUMX
    1.05
     Jefus
    1.04
    ^(@)
    1.04
     "¿
    1.04
    Act Density 0.234%

    No Known Activations