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

    Neuronpedia

    INDEX
    Explanations

    mathematical equalities and expressions involving equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Guen
    -0.69
     #
    -0.67
     Mendez
    -0.64
     her
    -0.63
     Alvarez
    -0.63
     to
    -0.63
     be
    -0.63
    pekt
    -0.63
     /
    -0.62
     Aitken
    -0.62
    POSITIVE LOGITS
     itſelf
    1.28
    &=&\
    1.25
     myſelf
    1.25
    &=&
    1.20
     Efq
    1.19
     &=&
    1.18
     ་་
    1.17
     themſelves
    1.16
     Anſ
    1.13
     Monfieur
    1.13
    Act Density 0.006%

    No Known Activations