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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations or symbols, particularly related to cardinality and set theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shroud
    -0.75
     charm
    -0.69
     Ago
    -0.65
     management
    -0.64
     denial
    -0.62
     Memories
    -0.62
     secrecy
    -0.62
     Mayhem
    -0.62
     Aware
    -0.61
     Ukrain
    -0.61
    POSITIVE LOGITS
    frac
    1.35
    times
    1.11
    Delta
    1.09
    text
    1.07
    begin
    1.06
    circ
    1.05
    sum
    1.04
    cal
    1.00
    sq
    0.99
    alpha
    0.98
    Act Density 0.006%

    No Known Activations