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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate contrast or exceptions

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

    following "but"

    np_acts-logits-general · gemini-2.0-flash

    contrast conj

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unit
    -0.55
    IsMutable
    -0.53
    //
    -0.51
    gül
    -0.49
    bootstrapcdn
    -0.48
    anyon
    -0.48
    $_['
    -0.47
     AssemblyProduct
    -0.47
    Unit
    -0.47
    larna
    -0.46
    POSITIVE LOGITS
     generally
    1.04
    generally
    1.00
     usually
    0.86
    Mostly
    0.84
     mostly
    0.84
     Mostly
    0.83
     generalmente
    0.82
    Generally
    0.82
     typically
    0.81
    mostly
    0.81
    Act Density 0.291%

    No Known Activations