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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or constructs related to mathematical concepts or logic

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Personensuche
    -1.13
    Personendaten
    -1.06
     дописавши
    -1.05
    AddTagHelper
    -1.01
     مرئيه
    -1.01
    ArgsConstructor
    -0.98
    StructEnd
    -0.95
     للمعارف
    -0.91
    rungsseite
    -0.89
     gynhyrchwyd
    -0.88
    POSITIVE LOGITS
     n
    0.46
     
    0.43
    mouseup
    0.43
     base
    0.42
     l
    0.41
     mixed
    0.41
     vernac
    0.40
    hänge
    0.39
     day
    0.39
     per
    0.38
    Act Density 0.018%

    No Known Activations