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

    Neuronpedia

    INDEX
    Explanations

    quantifiers or symbols related to mathematical expressions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Holl
    -0.70
    malar
    -0.60
    lend
    -0.59
    ITECH
    -0.57
    ising
    -0.57
    Overrides
    -0.57
    isome
    -0.56
     cách
    -0.56
    Bras
    -0.56
    esten
    -0.55
    POSITIVE LOGITS
    dq
    1.01
    eeq
    0.96
     Iq
    0.96
    IQ
    0.95
     IQ
    0.92
    eq
    0.91
    iq
    0.90
     SQ
    0.90
    Aq
    0.89
    Iq
    0.87
    Act Density 0.157%

    No Known Activations