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

    Neuronpedia

    INDEX
    Explanations

    capitalization of specific terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Portail
    -0.74
    HasBeenSet
    -0.69
     Roskov
    -0.67
    ReusableCell
    -0.66
     متعلقه
    -0.65
     propOrder
    -0.64
    reuters
    -0.63
     kasarigan
    -0.61
    DeleteBehavior
    -0.60
     "]
    -0.60
    POSITIVE LOGITS
     iNdEx
    3.44
    ContainerState
    1.40
    yyb
    0.98
    AppMethodBeat
    0.88
    yym
    0.77
     intStringLen
    0.69
     yyb
    0.68
    iNdEx
    0.68
    yyv
    0.59
     yyhl
    0.58
    Act Density 0.001%

    No Known Activations