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

    Neuronpedia

    INDEX
    Explanations

    statistical data and numerical information related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orna
    -0.15
    uren
    -0.15
    uchs
    -0.15
    ullen
    -0.15
    ovnÃŃ
    -0.14
    agues
    -0.14
    neider
    -0.14
     cÃŃt
    -0.13
    mites
    -0.13
    ublic
    -0.13
    POSITIVE LOGITS
    ½
    0.15
    RAFT
    0.15
    ifton
    0.15
    WG
    0.15
    strup
    0.14
     Giang
    0.14
    continental
    0.14
    .syntax
    0.14
    iju
    0.14
    ephy
    0.13
    Act Density 0.205%

    No Known Activations