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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or separation characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ),
    -0.70
     ]
    -0.67
    '],
    -0.66
    "],
    -0.66
    ']
    -0.63
     })
    -0.63
    "):
    -0.63
    "]
    -0.62
     ")
    -0.62
     ')
    -0.61
    POSITIVE LOGITS
    }
    0.82
    EndGlobalSection
    0.53
    脚注の使い方
    0.52
     snippetHide
    0.50
    momix
    0.46
     aDecoder
    0.46
    addGap
    0.43
    0.42
    Tikang
    0.42
    awtextra
    0.41
    Act Density 0.108%

    No Known Activations