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

    Neuronpedia

    INDEX
    Explanations

    strings and punctuation in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \""
    -0.97
    　　“
    -0.92
    }}"
    -0.90
    ”
    -0.86
    ]["
    -0.85
    “
    -0.85
    matmul
    -0.84
     $("<
    -0.84
    (",")
    -0.82
     Bartol
    -0.82
    POSITIVE LOGITS
    !='
    1.06
     '
    1.04
    ==='
    0.97
     '';
    0.97
    Ndr
    0.97
    >';
    0.96
    +'
    0.94
    ='.$
    0.94
     '.
    0.94
    ]='\
    0.94
    Act Density 0.207%

    No Known Activations