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

    Neuronpedia

    INDEX
    Explanations

    terms related to warranties and liability disclaimers

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

    warranties or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Foot
    -0.43
     Foot
    -0.43
    egt
    -0.42
     dic
    -0.42
     Adult
    -0.42
     Nex
    -0.41
    犯
    -0.40
    dictionary
    -0.40
     Missing
    -0.40
    rej
    -0.40
    POSITIVE LOGITS
     WARRANTIES
    3.52
     warranties
    1.36
     WARRANTY
    1.14
     warranty
    0.98
    Warranty
    0.88
     Warranty
    0.88
    warranty
    0.87
    warran
    0.81
     MERCHANTABILITY
    0.77
     GARANT
    0.74
    Act Density 0.001%

    No Known Activations