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

    Neuronpedia

    INDEX
    Explanations

    variables and mathematical symbols or notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лтамалар
    -0.43
    밌
    -0.41
    +#+#
    -0.41
     kasarigan
    -0.39
    ÊNCIA
    -0.39
    PerformLayout
    -0.38
     utafitiHapana
    -0.36
    诰
    -0.36
     autorytatywna
    -0.36
    tadiene
    -0.36
    POSITIVE LOGITS
     equals
    0.88
     equal
    0.80
     equ
    0.72
     igual
    0.66
    equals
    0.65
    equal
    0.65
     equalled
    0.65
     рав
    0.61
     bằng
    0.60
     EQUAL
    0.60
    Act Density 0.926%

    No Known Activations