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

    Neuronpedia

    INDEX
    Explanations

    numerical percentages and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unate
    -0.15
    د
    -0.15
     Economy
    -0.15
     bl
    -0.14
    меÑĢ
    -0.14
    enek
    -0.14
    pline
    -0.14
     economy
    -0.14
     twist
    -0.14
    sea
    -0.14
    POSITIVE LOGITS
    99
    0.38
    999
    0.34
    95
    0.22
    9
    0.18
    997
    0.18
    ९
    0.17
     ninety
    0.17
    98
    0.17
     Ninth
    0.17
    97
    0.17
    Act Density 0.046%

    No Known Activations