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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "same" followed by a positive integer, indicating similarity or repetition

    oai_token-act-pair · gpt-3.5-turbo

    references to similarity or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    *=-
    -0.76
    ONSORED
    -0.72
    rend
    -0.72
    orial
    -0.71
     Democr
    -0.70
     Provided
    -0.70
     Lauder
    -0.69
    pac
    -0.68
    olate
    -0.68
    ç«
    -0.67
    POSITIVE LOGITS
     kinds
    0.98
     thing
    0.97
     exact
    0.96
     amount
    0.89
     sorts
    0.88
     fate
    0.88
     kind
    0.84
     vein
    0.81
     ol
    0.78
     sort
    0.77
    Act Density 0.046%

    No Known Activations