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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to watching or observing events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.48
    lineTo
    -0.45
     répondu
    -0.44
     känd
    -0.44
    pegno
    -0.44
     answered
    -0.44
    afka
    -0.43
     étui
    -0.43
     речь
    -0.42
    ylated
    -0.42
    POSITIVE LOGITS
     watching
    2.51
     Watching
    2.31
    Watching
    2.28
     watch
    2.19
    watching
    2.19
     watched
    2.18
     witnessing
    2.07
     watches
    2.03
     observing
    2.02
     observation
    1.93
    Act Density 0.347%

    No Known Activations