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

    Neuronpedia

    INDEX
    Explanations

    references to watching and lists of things to be watched

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Abp
    -0.86
    }}],
    -0.80
    ']),
    -0.78
    />";
    -0.77
    ])),
    -0.77
    достатки
    -0.76
     Damien
    -0.76
    ◆◆
    -0.76
     للمعارف
    -0.75
    cycline
    -0.74
    POSITIVE LOGITS
     Watch
    2.01
     watch
    1.95
     WATCH
    1.90
     watches
    1.84
    Watch
    1.84
    watch
    1.83
    WATCH
    1.71
     Watches
    1.70
    watches
    1.66
     watched
    1.46
    Act Density 0.027%

    No Known Activations