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

    Neuronpedia

    INDEX
    Explanations

    expressions related to pushing boundaries or limits in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.47
    éez
    -0.42
     समीक्षाएं
    -0.40
     المعيارى
    -0.39
    CppCodeGen
    -0.38
     opérés
    -0.37
     kokona
    -0.37
     recevez
    -0.37
     venido
    -0.36
     milhares
    -0.35
    POSITIVE LOGITS
     Pushing
    0.69
    Pushing
    0.67
    stretched
    0.67
     pushes
    0.66
     pushing
    0.64
     stretching
    0.64
     desafi
    0.63
     stretched
    0.63
     stretch
    0.62
     Stretching
    0.62
    Act Density 0.292%

    No Known Activations