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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erable
    -0.17
    ths
    -0.17
    pector
    -0.17
    Ùĩ
    -0.17
    áce
    -0.15
    eriod
    -0.15
    inkel
    -0.15
    edy
    -0.14
    atic
    -0.14
    itzer
    -0.14
    POSITIVE LOGITS
    uate
    0.22
    uated
    0.22
    uality
    0.21
    ually
    0.21
    uating
    0.18
    uator
    0.17
    uation
    0.17
    ivia
    0.17
    alan
    0.16
    UAL
    0.16
    Act Density 0.044%

    No Known Activations