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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "large" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BoxShadow
    -0.68
     cumpli
    -0.66
    жидан
    -0.64
     Escobar
    -0.64
     jadi
    -0.63
     siguran
    -0.63
    новен
    -0.63
     régal
    -0.62
     πως
    -0.62
     expériment
    -0.62
    POSITIVE LOGITS
    LARGE
    1.33
    Large
    1.31
     Large
    1.31
     LARGE
    1.29
     large
    1.22
    large
    1.15
     larges
    1.07
    Small
    0.98
     larg
    0.97
     Small
    0.96
    Act Density 0.064%

    No Known Activations