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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a relationship between variables or parameters within a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Портал
    -0.54
     المعيارى
    -0.53
    ArgsConstructor
    -0.51
     unknownFields
    -0.48
    SPATH
    -0.48
    msgTypes
    -0.48
    afficheront
    -0.47
    슷
    -0.45
     plate
    -0.45
    ]='\
    -0.45
    POSITIVE LOGITS
     function
    3.74
    function
    3.32
     Function
    3.11
    Function
    2.88
     FUNCTION
    2.83
     functions
    2.74
     fonction
    2.67
    FUNCTION
    2.51
     función
    2.41
     func
    2.41
    Act Density 0.514%

    No Known Activations