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

    Neuronpedia

    INDEX
    Explanations

    architectural elements and characteristics of buildings or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ultz
    -0.16
    &eacute
    -0.16
     salopes
    -0.14
     Beats
    -0.14
    ìłĿ
    -0.14
    оÑĢо
    -0.13
    uld
    -0.13
    ummer
    -0.13
    (...)↵
    -0.13
    еÑĢж
    -0.13
    POSITIVE LOGITS
     ;
    0.19
     :
    0.16
     whereas
    0.15
     car
    0.15
     Whereas
    0.15
     whence
    0.15
     :↵↵
    0.15
    ,âĢ¦↵↵
    0.15
    stab
    0.14
     incl
    0.14
    Act Density 0.049%

    No Known Activations