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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.52
     isComment
    -0.52
    sifs
    -0.52
     isNameExpr
    -0.51
    ptonshire
    -0.50
    estanding
    -0.50
    dater
    -0.50
    ClCompile
    -0.49
     côté
    -0.48
    utnik
    -0.47
    POSITIVE LOGITS
     mean
    1.34
     MEAN
    1.03
    mean
    0.98
     Mean
    0.97
    Mean
    0.94
    MEAN
    0.81
     think
    0.67
     '\\;'
    0.54
    MemoryWarning
    0.54
    RectangleBorder
    0.54
    Act Density 0.112%

    No Known Activations