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

    Neuronpedia

    INDEX
    Explanations

    references to theories, philosophies, and scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄIJT
    -0.17
    yor
    -0.16
    ůž
    -0.16
    åį·
    -0.15
    \application
    -0.14
    ذر
    -0.14
    NESS
    -0.14
    çģ
    -0.14
    zet
    -0.13
    ANCED
    -0.13
    POSITIVE LOGITS
     referred
    0.30
     called
    0.29
    称
    0.28
     simply
    0.27
     gá»įi
    0.25
    called
    0.24
     call
    0.24
    稱
    0.23
    åı«
    0.23
     refer
    0.22
    Act Density 0.083%

    No Known Activations