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

    Neuronpedia

    INDEX
    Explanations

    various usages and references to the term "name" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.61
     /\.(
    -0.57
     /\.
    -0.53
    HomeAsUpEnabled
    -0.53
    permum
    -0.53
    nombre
    -0.50
    Name
    -0.47
     CURIAM
    -0.46
    aarrggbb
    -0.45
    rxjs
    -0.45
    POSITIVE LOGITS
    plate
    1.12
    plates
    1.00
    PLATE
    0.77
    akes
    0.73
     plate
    0.72
    Surname
    0.71
    Plate
    0.70
    Space
    0.70
     plates
    0.70
     Plates
    0.69
    Act Density 0.125%

    No Known Activations