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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    kloped
    -0.50
    )_/¯
    -0.50
    omir
    -0.49
    figure
    -0.49
     V
    -0.48
     Fig
    -0.48
    \{\\
    -0.47
     @"/
    -0.47
    _));
    -0.47
    듭
    -0.46
    POSITIVE LOGITS
     ſmall
    0.76
     ſeveral
    0.75
     Monfieur
    0.75
     Diſ
    0.71
     myſelf
    0.69
     themſelves
    0.69
     purpoſe
    0.68
     Houſe
    0.64
     parlando
    0.64
     pleaſure
    0.64
    Act Density 0.016%

    No Known Activations