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

    Neuronpedia

    INDEX
    Explanations

    the presence of the beginning of new segments in the text, such as section markers or conversation prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.51
     F
    -0.50
     R
    -0.50
     L
    -0.49
     W
    -0.49
    iecie
    -0.47
     E
    -0.47
     But
    -0.46
     Press
    -0.46
     V
    -0.45
    POSITIVE LOGITS
    SharedDtor
    0.81
     */;
    0.78
    ScopeManager
    0.77
     propTypes
    0.73
    TagMode
    0.71
     Paragon
    0.69
    脚注の使い方
    0.68
     Sociale
    0.66
     yonder
    0.66
     Química
    0.66
    Act Density 0.001%

    No Known Activations