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

    Neuronpedia

    INDEX
    Explanations

    the word "uses" indicating applications or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.71
     magnitudes
    -0.60
    DDG
    -0.59
     worshipped
    -0.58
     Causes
    -0.58
     Kanpur
    -0.58
     magnitude
    -0.58
     Madras
    -0.57
     repatriation
    -0.56
    causes
    -0.53
    POSITIVE LOGITS
     uses
    1.35
    Uses
    1.35
     Uses
    1.32
     USES
    1.09
     usos
    0.87
    uses
    0.79
    SequentialGroup
    0.78
    TagMode
    0.76
    };*/
    0.73
    LookAnd
    0.72
    Act Density 0.078%

    No Known Activations