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

    Neuronpedia

    INDEX
    Explanations

    patterns related to mathematical equations and functions

    oai_token-act-pair · gpt-3.5-turbo

    closing braces in mathematical expressions or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworks
    -0.89
    assador
    -0.82
    sembly
    -0.81
    estone
    -0.79
    ascus
    -0.79
    htaking
    -0.77
    ngth
    -0.76
    ateur
    -0.75
    uga
    -0.72
    mble
    -0.71
    POSITIVE LOGITS
    },
    0.89
    âĶĢâĶĢ
    0.84
    \)
    0.83
    ··
    0.80
    ]}
    0.80
    else
    0.80
    GROUP
    0.78
    ({
    0.77
     />
    0.75
    $$
    0.75
    Act Density 0.014%

    No Known Activations