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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the process of determining or classifying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    determin
    -0.81
     determines
    -0.81
     determining
    -0.73
     determine
    -0.73
    determine
    -0.70
    Determine
    -0.70
     détermin
    -0.68
     determinar
    -0.66
     Determining
    -0.65
     determina
    -0.65
    POSITIVE LOGITS
    最快更新
    0.42
    //
    0.40
    ëren
    0.40
    TagMode
    0.37
     Peer
    0.37
     Level
    0.37
     quality
    0.36
     qualifié
    0.36
     [*]
    0.36
     pinggang
    0.35
    Act Density 0.015%

    No Known Activations