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

    Neuronpedia

    INDEX
    Explanations

    references to personal identifiers or familial relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AsUp
    -0.79
     Monfieur
    -0.76
     Reſ
    -0.75
    ecap
    -0.74
     purpoſe
    -0.71
    simpleType
    -0.70
     chofe
    -0.69
     Efq
    -0.69
     themſelves
    -0.69
     ſmall
    -0.68
    POSITIVE LOGITS
     or
    0.62
    gebras
    0.50
     kasarigan
    0.47
     section
    0.46
     home
    0.45
     and
    0.45
    washingtonpost
    0.44
     menu
    0.44
     $\
    0.43
    址
    0.42
    Act Density 0.037%

    No Known Activations