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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conclusions or endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.77
    ])));
    -0.75
     INTERESAR
    -0.71
    ]$}
    -0.70
    ']))
    -0.70
    ]))
    -0.64
    })));
    -0.63
    shadowOpacity
    -0.63
    })$}
    -0.62
    "]').
    -0.62
    POSITIVE LOGITS
     ended
    1.57
     ending
    1.48
     Ending
    1.41
     Ended
    1.35
     ends
    1.34
     Ends
    1.23
    Ending
    1.23
    Ended
    1.20
    ended
    1.07
     endings
    1.07
    Act Density 0.163%

    No Known Activations