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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.83
     
    -0.83
     of
    -0.76
    ,
    -0.76
    <eos>
    -0.76
     and
    -0.76
     is
    -0.75
     also
    -0.74
     in
    -0.72
     ,
    -0.69
    POSITIVE LOGITS
     kaarangay
    1.48
    Autoritní
    1.39
     Савезне
    1.38
     Paglinawan
    1.38
     Roskov
    1.31
    __':
    1.26
    1.26
     autorytatywna
    1.24
     myſelf
    1.23
    ArrowToggle
    1.20
    Act Density 3.525%

    No Known Activations