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

    Neuronpedia

    INDEX
    Explanations

    quantitative data or statistics related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íħĶ
    -0.15
    chg
    -0.14
    ÑĮко
    -0.14
    ufig
    -0.14
    cak
    -0.14
    ades
    -0.14
    /manual
    -0.14
     Ná»Ļi
    -0.13
    mdp
    -0.13
    bach
    -0.13
    POSITIVE LOGITS
    piration
    0.14
     Vis
    0.14
     Sail
    0.14
    listener
    0.14
     Chevron
    0.13
     nackte
    0.13
    iyan
    0.13
     recon
    0.13
     Pit
    0.13
    ivor
    0.13
    Act Density 0.038%

    No Known Activations