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

    Neuronpedia

    INDEX
    Explanations

    references to limits, conditions, and capacities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĦst
    -0.15
     ÄĮer
    -0.15
    akes
    -0.15
    Endpoints
    -0.15
    _exclude
    -0.14
     Cav
    -0.14
    istra
    -0.14
     cav
    -0.13
    achinery
    -0.13
    akhir
    -0.13
    POSITIVE LOGITS
     Exhaust
    0.22
     exhausted
    0.22
     exhaust
    0.21
     cannot
    0.20
     Limits
    0.19
     exceeding
    0.18
     exhausting
    0.18
    Limits
    0.18
     saturation
    0.17
     exceeded
    0.17
    Act Density 0.005%

    No Known Activations