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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to enjoyment or dissatisfaction with media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding "watch" or "watching"

    np_acts-logits-general · gemini-2.0-flash

    watching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.60
     Segurança
    -0.51
     Tarn
    -0.51
    writeFieldEnd
    -0.50
    Прода
    -0.50
    thâu
    -0.49
    jooq
    -0.49
     Microphone
    -0.48
    etragen
    -0.48
    UnknownFieldSet
    -0.48
    POSITIVE LOGITS
     watch
    3.27
     watching
    3.17
     watched
    2.93
     Watch
    2.83
     Watching
    2.77
    watch
    2.76
     watches
    2.75
    Watch
    2.71
     WATCH
    2.69
    watching
    2.67
    Act Density 0.326%

    No Known Activations