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

    Neuronpedia

    INDEX
    Explanations

    concepts related to algorithms and evaluations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quez
    -0.16
    acman
    -0.15
    leys
    -0.15
    rete
    -0.14
    istrovstvÃŃ
    -0.14
    orz
    -0.14
    ÑĢÑĥг
    -0.14
    inherits
    -0.14
    ieren
    -0.14
    834
    -0.14
    POSITIVE LOGITS
     tracks
    0.39
     measures
    0.36
     sorts
    0.29
     Measures
    0.29
     Tracks
    0.28
     determines
    0.27
     monitors
    0.27
     reviews
    0.25
     checks
    0.25
     loc
    0.24
    Act Density 0.154%

    No Known Activations