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

    Neuronpedia

    INDEX
    Explanations

    not equal conditions or non-membership in defined sets

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

    not equal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.62
    SerializedSize
    -0.52
     متعلقه
    -0.48
    /*
    -0.47
    ulemon
    -0.47
    Joel
    -0.45
    above
    -0.43
    carl
    -0.42
    starting
    -0.42
    Caitlin
    -0.41
    POSITIVE LOGITS
    neq
    1.93
    ≠
    1.04
    ddagger
    0.93
     ≠
    0.92
     different
    0.59
     khác
    0.56
     Different
    0.54
    notin
    0.51
    Different
    0.50
     fact
    0.47
    Act Density 0.012%

    No Known Activations