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

    Neuronpedia

    INDEX
    Explanations

    visual elements or indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quet
    -0.18
    ìĭĿ
    -0.17
    ker
    -0.16
    ruh
    -0.16
    Authority
    -0.15
    æŀ¶
    -0.15
    tal
    -0.14
    ergus
    -0.14
     Fist
    -0.14
    lac
    -0.14
    POSITIVE LOGITS
    Dispose
    0.16
    ÑĢап
    0.16
    ssi
    0.16
    ÐłÐŀ
    0.15
    orro
    0.15
    Pager
    0.14
    SL
    0.14
    Å¡el
    0.14
    ีย
    0.14
    adier
    0.14
    Act Density 0.001%

    No Known Activations