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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptions and measurements related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asha
    -0.14
    urope
    -0.13
    yster
    -0.13
     hairs
    -0.13
    ì¶Ķ
    -0.13
    iti
    -0.13
     Conv
    -0.13
     chua
    -0.13
    áct
    -0.13
    conv
    -0.13
    POSITIVE LOGITS
    eko
    0.15
    rej
    0.15
    exels
    0.14
    agedList
    0.14
    agli
    0.14
     Weber
    0.14
    ÑģÑĮого
    0.14
    gil
    0.14
    xes
    0.14
    мага
    0.14
    Act Density 0.121%

    No Known Activations