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

    Neuronpedia

    INDEX
    Explanations

    references to systems, processes, and their effectiveness or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ait
    -0.15
     Advocate
    -0.14
     advocate
    -0.14
     обла
    -0.14
     mediums
    -0.14
    CLU
    -0.13
    ischen
    -0.13
    alı
    -0.13
    horn
    -0.13
    bah
    -0.13
    POSITIVE LOGITS
     slow
    0.22
     labor
    0.21
     labour
    0.21
    Slow
    0.20
     slower
    0.20
    Sensitive
    0.20
    slow
    0.20
     sensitive
    0.19
     sensitivity
    0.19
     Slow
    0.18
    Act Density 0.016%

    No Known Activations