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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation used in textual representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCart
    -0.16
    erais
    -0.16
    resenter
    -0.15
    eli
    -0.15
    ãĥĭãĥ¡
    -0.15
    ÐĿÐIJ
    -0.14
    rale
    -0.14
    ланд
    -0.14
    UILayout
    -0.14
    -BEGIN
    -0.14
    POSITIVE LOGITS
    éĺ´
    0.15
    äºĭåĭĻ
    0.15
     volum
    0.14
    idelberg
    0.14
    343
    0.14
     Cleveland
    0.14
    aign
    0.14
    16
    0.14
     Campos
    0.14
     subtle
    0.13
    Act Density 0.075%

    No Known Activations