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

    Neuronpedia

    INDEX
    Explanations

    expressions of determination and intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.19
    vez
    -0.17
    ameda
    -0.17
    istrovstvÃŃ
    -0.16
    rax
    -0.16
    IntPtr
    -0.15
    culate
    -0.14
    pearance
    -0.14
    odium
    -0.14
    atories
    -0.14
    POSITIVE LOGITS
    ness
    0.16
     distr
    0.15
    anka
    0.14
    аÑĢан
    0.14
    NESS
    0.14
    WSTR
    0.14
    uteÄį
    0.14
    족
    0.13
    ãĥ³ãĥģ
    0.13
     obt
    0.13
    Act Density 0.025%

    No Known Activations