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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts and operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.68
     I
    -0.54
     which
    -0.54
    I
    -0.51
     my
    -0.49
     f
    -0.48
    (
    -0.48
     in
    -0.48
    اص
    -0.47
     fundo
    -0.47
    POSITIVE LOGITS
     Efq
    1.19
     Monfieur
    1.02
     $_"
    1.01
     pleaſure
    1.01
     myſelf
    1.00
     ་་
    1.00
    :✨
    0.98
     ſtate
    0.96
     auffi
    0.94
     Jefus
    0.94
    Act Density 0.005%

    No Known Activations