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

    Neuronpedia

    INDEX
    Explanations

    snippets of code or references to data bindings in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ').'</
    -0.21
    ')?></
    -0.20
    ');</
    -0.19
     ?>><?
    -0.19
     ?></
    -0.19
    }}</
    -0.18
     />)↵
    -0.18
    ');?></
    -0.18
    '].'</
    -0.17
    ')</
    -0.17
    POSITIVE LOGITS
    }">↵
    0.23
    Ŀ
    0.21
    }"
    0.20
    )">↵
    0.20
    }}">↵
    0.19
     Quote
    0.19
     )"
    0.18
     }}">↵
    0.18
    quot
    0.18
     ?>">č↵
    0.17
    Act Density 0.015%

    No Known Activations