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

    Neuronpedia

    INDEX
    Explanations

    the presence of multiple sections or instances of emphasis within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KEYCODE
    -0.90
    Билгалдахарш
    -0.87
     Signalez
    -0.84
     MediatR
    -0.83
    Gambas
    -0.82
     Exacts
    -0.78
     setuptools
    -0.78
    principalTable
    -0.78
    ++
    -0.77
    ngdoc
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.78
    ↵
    0.70
     zwar
    0.60
    <eos>
    0.59
      
    0.57
    ↵↵↵
    0.54
     although
    0.54
    Although
    0.52
     Although
    0.51
    Their
    0.50
    Act Density 0.151%

    No Known Activations