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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating a lesser degree or quantity

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

    much less, let alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.56
     AssemblyCulture
    -0.48
    Personensuche
    -0.47
     Constitucional
    -0.47
     ligiloj
    -0.46
     Komunikasi
    -0.46
     serpiente
    -0.46
    bootstrapcdn
    -0.45
     otomatig
    -0.44
    tinyos
    -0.44
    POSITIVE LOGITS
    まして
    0.42
    别说
    0.38
     melt
    0.37
     apalagi
    0.36
    krebs
    0.35
    cairn
    0.35
    Bathrooms
    0.35
     Forget
    0.35
    tab
    0.35
    opsis
    0.34
    Act Density 0.028%

    No Known Activations