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

    Neuronpedia

    INDEX
    Explanations

    references to statistical and mathematical concepts related to variance and estimators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    lidades
    -0.62
    ampunk
    -0.62
     
    -0.59
    thschild
    -0.59
    ước
    -0.59
     Caw
    -0.55
    울
    -0.55
    sul
    -0.55
     Ste
    -0.54
     userService
    -0.54
    POSITIVE LOGITS
    Sigma
    1.42
     Sigma
    1.31
     pleaſure
    1.22
     myſelf
    1.03
    Σ
    1.03
     تانيه
    1.02
     bershka
    1.02
     Inscrivez
    1.00
     Σ
    0.98
     himſelf
    0.96
    Act Density 0.004%

    No Known Activations