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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that could represent data structures or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     been
    -0.79
     McKenna
    -0.73
     sugar
    -0.72
    GraphicsUnit
    -0.69
    man
    -0.67
     Plank
    -0.67
     back
    -0.65
    ader
    -0.64
     K
    -0.64
     a
    -0.63
    POSITIVE LOGITS
    +#+
    1.24
    ]--;
    1.13
    ]},
    1.06
    },
    1.05
    )},
    1.01
     "..\..\..\
    1.01
    }}],
    0.99
     plufieurs
    0.96
    "}},
    0.96
    }}},
    0.96
    Act Density 0.362%

    No Known Activations