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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing differences in measurements or comparisons of data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cyfarwyddwr
    -0.39
     createSprite
    -0.38
     الحره
    -0.37
     متعلقه
    -0.35
    UESDAY
    -0.35
    cuado
    -0.32
     Unab
    -0.31
    tirer
    -0.31
    //
    -0.31
    uchungen
    -0.31
    POSITIVE LOGITS
     difference
    3.56
     differences
    3.20
    difference
    3.14
     Difference
    3.06
    Difference
    3.00
     Differences
    2.91
    Differences
    2.83
     DIFFERENCE
    2.81
    differences
    2.80
     différence
    2.75
    Act Density 1.667%

    No Known Activations