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

    Neuronpedia

    INDEX
    Explanations

    terms related to deterioration and decay

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

    rot and decay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.86
    tagHelperRunner
    -0.64
     surla
    -0.60
    featureID
    -0.57
    parsedMessage
    -0.57
    BagConstraints
    -0.52
    Personendaten
    -0.51
    GEBURTSDATUM
    -0.51
     MainAxisSize
    -0.50
    hObject
    -0.50
    POSITIVE LOGITS
     rotten
    1.04
     rotting
    0.94
     decay
    0.81
     Decay
    0.75
     Rotten
    0.75
     decaying
    0.75
    rotten
    0.73
    Decay
    0.72
     decayed
    0.70
     rot
    0.69
    Act Density 0.026%

    No Known Activations