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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the motivations behind actions and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anz
    -0.16
    ulo
    -0.15
     Bomb
    -0.15
    ux
    -0.15
    EI
    -0.15
     Jury
    -0.15
     title
    -0.15
    EP
    -0.14
    HZ
    -0.14
    irus
    -0.14
    POSITIVE LOGITS
    mant
    0.19
    ắt
    0.17
     tô
    0.16
    วà¸Ļ
    0.16
    ICODE
    0.16
     useStyles
    0.16
    ç½
    0.15
    ãĥ¬ãĥ³
    0.15
    èŤ
    0.15
    urance
    0.15
    Act Density 0.213%

    No Known Activations