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

    Neuronpedia

    INDEX
    Explanations

    references to scientific measurements and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _ck
    -0.15
    977
    -0.15
    esus
    -0.15
    urg
    -0.15
     Klo
    -0.15
    celik
    -0.15
     helicopt
    -0.14
    esiz
    -0.14
    pollo
    -0.14
    hausen
    -0.14
    POSITIVE LOGITS
    roat
    0.17
    alary
    0.16
    Regressor
    0.15
    ãĤıãģij
    0.14
    _SHIFT
    0.14
     Leonard
    0.13
    umer
    0.13
    SHIFT
    0.13
     reign
    0.13
    енко
    0.13
    Act Density 0.011%

    No Known Activations