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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'n' and variations in adjacent characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =$?
    -1.04
    .}~\
    -1.02
     }^{*}
    -0.95
    >");
    -0.95
     $_"
    -0.92
    leſs
    -0.92
    leuth
    -0.92
    .";
    -0.91
    σθαι
    -0.88
    ждую
    -0.87
    POSITIVE LOGITS
    \
    0.87
    seamnă
    0.73
       
    0.73
      
    0.73
    ↵
    0.72
    P
    0.71
    V
    0.70
     Silurian
    0.69
    S
    0.69
    0.68
    Act Density 0.099%

    No Known Activations