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

    Neuronpedia

    INDEX
    Explanations

    negative assessments of movies or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alace
    -0.16
    imid
    -0.16
    ÑģиÑĤ
    -0.15
    -BEGIN
    -0.14
    cko
    -0.13
     Invasion
    -0.13
    éĻº
    -0.13
    awning
    -0.13
    ì°°
    -0.13
    _Ptr
    -0.13
    POSITIVE LOGITS
     death
    0.78
     died
    0.77
     deaths
    0.73
     dying
    0.70
     dies
    0.68
     dead
    0.67
     die
    0.65
    æŃ»
    0.64
    death
    0.61
    æŃ»äº¡
    0.60
    Act Density 0.984%

    No Known Activations