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

    Neuronpedia

    INDEX
    Explanations

    terms related to coding such as specific functions and variable names

    oai_token-act-pair · gpt-3.5-turbo

    programming code structures, particularly function and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.89
    theless
    -0.72
    shed
    -0.71
    ĵĺ
    -0.71
    maxwell
    -0.70
     mathemat
    -0.69
    cipled
    -0.65
     defic
    -0.64
    URA
    -0.64
    hement
    -0.62
    POSITIVE LOGITS
     ))
    1.33
    ))
    1.26
     ));
    1.19
    )))
    1.18
    )"
    1.15
     ])
    1.13
    ))))
    1.13
     )]
    1.11
     )
    1.10
     })
    1.09
    Act Density 0.081%

    No Known Activations