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

    Neuronpedia

    INDEX
    Explanations

    programming-related comments and documentation annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.53
     =
    -0.51
    ,
    -0.51
     .
    -0.50
     :
    -0.49
    :
    -0.48
     vi
    -0.47
    .:
    -0.47
     flat
    -0.47
     Mor
    -0.47
    POSITIVE LOGITS
     الرياضيه
    1.12
     }}$}
    1.08
    \}\\
    1.07
     ་་
    1.01
     itſelf
    0.97
    }}$\\
    0.97
    SequentialGroup
    0.96
     "
    0.95
    \\
    0.92
     *
    0.92
    Act Density 0.162%

    No Known Activations