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

    Neuronpedia

    INDEX
    Explanations

    references to capital cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     —
    -0.17
    odega
    -0.17
     ;
    -0.17
     —↵
    -0.17
     [âĢ¦]↵↵
    -0.16
     —↵↵
    -0.16
     ,↵
    -0.16
    ollar
    -0.16
     [*
    -0.16
     specialised
    -0.15
    POSITIVE LOGITS
     plus
    0.17
     whilst
    0.17
     cowork
    0.15
     defense
    0.15
    libs
    0.15
     WIFI
    0.15
    imentary
    0.14
    iggins
    0.14
     folk
    0.14
     odd
    0.14
    Act Density 0.000%

    No Known Activations