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

    Neuronpedia

    INDEX
    Explanations

    specific website addresses and technical references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hardt
    -0.17
    orta
    -0.16
    æ´ŀ
    -0.16
    ÑĢÑĥб
    -0.15
    _dll
    -0.15
    rada
    -0.15
    ASSES
    -0.15
     гÑĢи
    -0.14
    imers
    -0.14
    emp
    -0.14
    POSITIVE LOGITS
    atego
    0.23
    士
    0.19
    quared
    0.16
    strict
    0.15
    ÅĤa
    0.14
    alth
    0.14
    amarin
    0.14
    dge
    0.14
    830
    0.13
    DMI
    0.13
    Act Density 0.034%

    No Known Activations