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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific formatted code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.09
     Anſ
    -0.96
     ſeveral
    -0.91
     iconFacebook
    -0.89
     ་་
    -0.89
     myſelf
    -0.89
     ―――――
    -0.88
     verſ
    -0.88
     ſever
    -0.87
     themſelves
    -0.86
    POSITIVE LOGITS
     x
    1.09
     S
    0.95
     P
    0.94
    xH
    0.93
     g
    0.92
     G
    0.88
     T
    0.88
     B
    0.88
     p
    0.87
     M
    0.87
    Act Density 0.139%

    No Known Activations