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

    Neuronpedia

    INDEX
    Explanations

    code and markup syntax elements typically found in programming or data markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unga
    -0.17
     w
    -0.17
    ä¼Ĺ
    -0.16
     about
    -0.15
    adm
    -0.15
     h
    -0.14
    çľ¾
    -0.14
     Western
    -0.14
    ,
    -0.14
    ;
    -0.14
    POSITIVE LOGITS
    uzu
    0.16
    esine
    0.15
    osal
    0.14
    елиÑĩ
    0.14
    azel
    0.14
    ulet
    0.14
    нима
    0.13
    ümÃ¼ÅŁ
    0.13
    _WS
    0.13
     nackte
    0.13
    Act Density 0.001%

    No Known Activations