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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments towards characters in movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ochen
    -0.19
    icker
    -0.19
    åĨµ
    -0.16
    esel
    -0.16
    åĿĬ
    -0.16
    uzzi
    -0.16
    ometr
    -0.15
    .utf
    -0.15
     Vulner
    -0.15
    zel
    -0.15
    POSITIVE LOGITS
     repell
    0.18
    roc
    0.15
     boredom
    0.14
     worse
    0.14
    æĭĴ
    0.14
     worst
    0.14
     WARRANT
    0.14
    exit
    0.14
     Chap
    0.14
    .spark
    0.14
    Act Density 0.173%

    No Known Activations