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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets and syntax

    oai_token-act-pair · gpt-3.5-turbo

    syntactic structures and elements related to programming or computer code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACTIONS
    -0.79
    EVA
    -0.66
     spons
    -0.63
    BILITIES
    -0.59
     reconc
    -0.57
     DRAG
    -0.55
     Invention
    -0.55
     behavi
    -0.55
     intakes
    -0.54
     confir
    -0.54
    POSITIVE LOGITS
    ]"
    1.82
    ']
    1.82
    })
    1.78
    }
    1.77
    }}
    1.75
    "]
    1.69
    ]
    1.69
    }"
    1.65
    ]]
    1.60
    ],
    1.60
    Act Density 0.149%

    No Known Activations