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

    Neuronpedia

    INDEX
    Explanations

    the concept of goals and their optimization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceum
    -0.58
    íslu
    -0.56
     bedien
    -0.56
     dizaine
    -0.54
     عص
    -0.53
     It
    -0.52
    ITC
    -0.52
     ocurrió
    -0.52
     مستقیم
    -0.52
     erős
    -0.52
    POSITIVE LOGITS
     goals
    2.17
     Goals
    2.16
     Goal
    2.16
     GOAL
    2.11
     goal
    2.04
    goal
    1.98
    goals
    1.97
    Goals
    1.97
     GOALS
    1.97
    Goal
    1.96
    Act Density 0.050%

    No Known Activations