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

    Neuronpedia

    INDEX
    Explanations

    references to relationships or dependency dynamics among multiple subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Other
    -0.14
    ãģĻãĤĮãģ°
    -0.13
     dansk
    -0.13
    ä»ĸãģ®
    -0.13
    ĢìĿ´
    -0.13
    ãģĭãģ«
    -0.13
     diÄŁer
    -0.13
     οÏĢοίο
    -0.13
    Č↵
    -0.12
     extraordin
    -0.12
    POSITIVE LOGITS
     many
    0.66
     some
    0.58
    many
    0.53
     none
    0.52
    some
    0.47
     most
    0.44
    none
    0.43
     Many
    0.42
     each
    0.41
     Some
    0.39
    Act Density 0.331%

    No Known Activations