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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to engineering and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oga
    -0.18
    rete
    -0.15
    åĦ
    -0.15
    kla
    -0.15
    tempt
    -0.14
     âĹĦ
    -0.14
     bounty
    -0.14
    rosso
    -0.14
    _hook
    -0.13
     Landscape
    -0.13
    POSITIVE LOGITS
     lubric
    0.42
     Lub
    0.37
     trib
    0.35
     lub
    0.34
    lub
    0.32
     Trib
    0.29
    润
    0.28
     journal
    0.28
     grease
    0.28
     wear
    0.27
    Act Density 0.045%

    No Known Activations