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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    chance of outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Krä
    -0.53
    เจ้า
    -0.45
    akterysty
    -0.44
     texts
    -0.43
    Das
    -0.43
    unfinished
    -0.42
     Das
    -0.42
    тря
    -0.42
    aujourd
    -0.41
     McM
    -0.41
    POSITIVE LOGITS
     ujednoznacz
    0.54
     chance
    0.52
     Chance
    0.50
    Chance
    0.46
    aarrggbb
    0.45
     Probability
    0.44
    HostException
    0.43
    espère
    0.42
    0.42
     eventual
    0.41
    Act Density 0.024%

    No Known Activations