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

    Neuronpedia

    INDEX
    Explanations

    instances of watching or observing actions and events

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

    watching events unfold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linkovi
    -0.46
     mergeFrom
    -0.42
    awtextra
    -0.41
    jsdelivr
    -0.40
     MainAxisSize
    -0.39
    imageshack
    -0.39
    CloseOperation
    -0.39
    spread
    -0.38
     probab
    -0.38
     Spread
    -0.38
    POSITIVE LOGITS
     watched
    0.60
    Losing
    0.56
     watching
    0.56
    Watching
    0.54
     losing
    0.54
    watched
    0.54
     Watching
    0.52
     kehilangan
    0.52
     helplessly
    0.51
     watch
    0.50
    Act Density 0.152%

    No Known Activations