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

    Neuronpedia

    INDEX
    Explanations

    references to decisions and collective agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    859
    -0.15
    ãģŃ
    -0.15
    ãģ«ãģª
    -0.14
    iez
    -0.14
    lena
    -0.13
     directly
    -0.13
    ses
    -0.13
    otas
    -0.13
    Overlap
    -0.13
    vidence
    -0.13
    POSITIVE LOGITS
     decision
    0.27
     decide
    0.26
     decides
    0.25
     decided
    0.23
     deciding
    0.23
     Decide
    0.23
    decision
    0.21
     Decision
    0.21
    Decision
    0.20
    決
    0.20
    Act Density 0.043%

    No Known Activations