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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in mathematical notation or symbolic representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -3.12
     itſelf
    -2.94
     Theſe
    -2.77
     Efq
    -2.77
     Anſ
    -2.76
     ―――――
    -2.71
    ſelf
    -2.69
     iſt
    -2.64
     Houſe
    -2.62
     Monfieur
    -2.61
    POSITIVE LOGITS
     \
    3.51
    \
    2.12
     
    1.77
     $\
    1.63
     (
    1.61
      
    1.55
    ↵
    1.48
     I
    1.41
     /
    1.41
     .
    1.39
    Act Density 0.201%

    No Known Activations