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

    Neuronpedia

    INDEX
    Explanations

    statistics related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    鹿
    -0.15
    oni
    -0.15
     unpaid
    -0.15
    å¿ľ
    -0.14
    inh
    -0.14
     Baldwin
    -0.14
     covering
    -0.14
    latlong
    -0.13
    mai
    -0.13
    miner
    -0.13
    POSITIVE LOGITS
    emoc
    0.17
    etur
    0.16
    Below
    0.15
     Haram
    0.14
    zac
    0.14
     FileAccess
    0.14
    ê¶Į
    0.14
    below
    0.14
    leftright
    0.14
    кÑĥл
    0.14
    Act Density 0.152%

    No Known Activations