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

    Neuronpedia

    INDEX
    Explanations

    terms related to optimization and ergonomic performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyph
    -0.17
    ned
    -0.16
    ittest
    -0.15
    awn
    -0.15
    sg
    -0.15
    lÃŃÄį
    -0.15
    letter
    -0.15
    ury
    -0.14
    rp
    -0.14
    ty
    -0.14
    POSITIVE LOGITS
    /max
    0.21
    -eff
    0.20
    imal
    0.19
    IMUM
    0.19
    /min
    0.18
    imum
    0.18
    istic
    0.17
    imize
    0.17
     conditions
    0.17
     performance
    0.16
    Act Density 0.019%

    No Known Activations