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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating duality or simultaneous occurrence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edo
    -0.16
    sey
    -0.16
    kj
    -0.15
    iert
    -0.14
    ieri
    -0.14
    illin
    -0.14
    esz
    -0.14
     BASIS
    -0.14
    elp
    -0.14
    arget
    -0.14
    POSITIVE LOGITS
    ravel
    0.15
    irs
    0.15
    exas
    0.15
    ë§ī
    0.14
    ould
    0.14
    ãģĿãĤĮãģ¯
    0.14
    rav
    0.14
    -fold
    0.14
    setter
    0.14
     Annunci
    0.13
    Act Density 0.035%

    No Known Activations