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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "watch" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jambes
    -0.60
     InputDecoration
    -0.59
     groter
    -0.59
     profondità
    -0.59
     idéia
    -0.58
     soggior
    -0.56
     renseignements
    -0.56
     tiks
    -0.54
    ])),
    -0.54
     montagna
    -0.53
    POSITIVE LOGITS
     watch
    1.45
     watched
    1.43
     Watched
    1.40
    Watched
    1.27
     WATCH
    1.24
    watched
    1.23
    Watching
    1.22
     watches
    1.22
     watching
    1.21
     Watch
    1.19
    Act Density 0.068%

    No Known Activations