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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical models and probability distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.61
    ">//
    -0.58
    watch
    -0.51
    ArgsConstructor
    -0.49
     conquer
    -0.48
    Watch
    -0.48
    療
    -0.48
    нено
    -0.47
    ThroughAttribute
    -0.47
    iren
    -0.47
    POSITIVE LOGITS
     probabilities
    0.84
     probabilidad
    0.82
     probability
    0.81
    probability
    0.77
    Probability
    0.75
    Probab
    0.74
    概率
    0.74
     Probability
    0.71
    bability
    0.71
    probab
    0.70
    Act Density 1.484%

    No Known Activations