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

    Neuronpedia

    INDEX
    Explanations

    different types of bracket characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŀ
    -0.19
    [
    -0.19
    "}↵↵
    -0.16
    "};↵↵
    -0.15
    ľ
    -0.15
    atis
    -0.14
    '}↵↵
    -0.14
    "};↵
    -0.14
    OrUpdate
    -0.14
    "});↵
    -0.14
    POSITIVE LOGITS
    !]
    0.28
    +]
    0.28
    ?]
    0.28
    {}]
    0.25
    .]
    0.24
     ]↵
    0.22
    ...]
    0.22
     ]
    0.21
    ÐIJÑĢÑħÑĸвовано
    0.21
     ],
    0.20
    Act Density 0.124%

    No Known Activations