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

    Neuronpedia

    INDEX
    Explanations

    terminology related to scientific processes or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zhou
    -0.70
    radura
    -0.70
    bault
    -0.69
    h
    -0.68
    åd
    -0.65
     ro
    -0.64
     Magdalene
    -0.64
    ТЕЛЬ
    -0.63
    bourhood
    -0.63
    もり
    -0.63
    POSITIVE LOGITS
    ])));
    1.58
    )])
    1.43
    ]));
    1.43
    ());
    1.42
    ]))
    1.41
    )));
    1.39
    ));
    1.38
    ')))
    1.35
    )})
    1.35
    ]))
    1.33
    Act Density 0.117%

    No Known Activations