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

    Neuronpedia

    INDEX
    Explanations

    instances of edits and updates in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    gatsby
    -0.59
    (&:
    -0.52
    enumi
    -0.49
     balles
    -0.47
    ind
    -0.46
     ό
    -0.46
    maine
    -0.44
     Alcott
    -0.44
     dos
    -0.43
    errors
    -0.43
    POSITIVE LOGITS
    InjectAttribute
    0.88
     Meksiku
    0.83
     Мексичка
    0.80
    躇
    0.80
     kaarangay
    0.77
     disponibilités
    0.77
     AspNetCore
    0.76
    styleType
    0.75
    cerely
    0.72
    OGND
    0.71
    Act Density 0.003%

    No Known Activations