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

    Neuronpedia

    INDEX
    Explanations

    instances of watching or witnessing events, particularly in a narrative or observational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pregn
    -0.16
    CRM
    -0.14
    mitter
    -0.14
    اسÛĮ
    -0.14
    xDB
    -0.14
    .addr
    -0.14
     Gim
    -0.14
     ÑģопÑĢов
    -0.13
    «a
    -0.13
    ilet
    -0.13
    POSITIVE LOGITS
     unfold
    0.22
     spectacle
    0.20
     phenomenon
    0.19
    unfold
    0.19
     watched
    0.18
     closely
    0.18
     happening
    0.18
    Watch
    0.18
     unfolding
    0.18
    watch
    0.17
    Act Density 0.177%

    No Known Activations