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

    Neuronpedia

    INDEX
    Explanations

    dialogues and conversational responses that express personal opinions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geile
    -0.17
    SGlobal
    -0.16
    .GroupLayout
    -0.16
    imestep
    -0.15
    gew
    -0.15
    .EventQueue
    -0.15
    ansi
    -0.15
    panse
    -0.15
     pornost
    -0.15
    .jdesktop
    -0.14
    POSITIVE LOGITS
    áºŃt
    0.17
    åľĪ
    0.16
     Hicks
    0.16
    charts
    0.14
    ff
    0.14
    acak
    0.14
    è¯Ŀ
    0.14
     rf
    0.13
     wide
    0.13
     wallet
    0.13
    Act Density 0.189%

    No Known Activations