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

    Neuronpedia

    INDEX
    Explanations

    emotional engagement with characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulas
    -0.17
    aca
    -0.15
    çĵ
    -0.14
    ushman
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    helm
    -0.14
    WORDS
    -0.14
     æĴ
    -0.14
    quat
    -0.14
    MeasureSpec
    -0.13
    POSITIVE LOGITS
     rooting
    0.36
     root
    0.32
     Root
    0.30
    Root
    0.27
    root
    0.26
    (root
    0.25
    /root
    0.25
     investment
    0.25
     ROOT
    0.24
     invested
    0.23
    Act Density 0.136%

    No Known Activations