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

    Neuronpedia

    INDEX
    Explanations

    overlapping themes and sentiments in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¨ãģĵãĤį
    -0.18
    .TODO
    -0.14
    ди
    -0.14
     Manor
    -0.14
    ãģ£ãģ
    -0.14
    arehouse
    -0.14
     Miscellaneous
    -0.14
    adin
    -0.14
     Vuex
    -0.13
     Vander
    -0.13
    POSITIVE LOGITS
    ellig
    0.16
    arto
    0.15
    RAINT
    0.15
    ive
    0.15
    ừng
    0.15
    ãģĵãĤĵãģ«
    0.14
    âng
    0.14
    kke
    0.14
    setattr
    0.14
    ewater
    0.14
    Act Density 0.006%

    No Known Activations