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

    Neuronpedia

    INDEX
    Explanations

    expressions related to numerical ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VisualStudio
    -0.51
     XVIII
    -0.48
     XIX
    -0.46
    nenie
    -0.45
    SharedCtor
    -0.44
     vis
    -0.43
     Spartan
    -0.42
    ur
    -0.42
    веду
    -0.42
     win
    -0.42
    POSITIVE LOGITS
     ranges
    1.04
    avg
    0.93
    ranges
    0.90
     avg
    0.83
     Ranges
    0.79
    Avg
    0.79
    Ranges
    0.79
    range
    0.74
     étrangère
    0.72
    pb
    0.70
    Act Density 0.121%

    No Known Activations