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

    Neuronpedia

    INDEX
    Explanations

    references to the subject "he."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     triom
    -0.66
    SourceChecksum
    -0.63
     disting
    -0.61
     Riccardo
    -0.60
     Wirt
    -0.57
     suspen
    -0.57
    bii
    -0.57
     verſ
    -0.56
     nui
    -0.56
     Découvrez
    -0.56
    POSITIVE LOGITS
    he
    2.80
    HE
    2.36
     HE
    2.30
     he
    2.02
    He
    1.92
     He
    1.72
    heli
    1.22
     helium
    1.21
    hes
    1.18
    she
    1.17
    Act Density 0.154%

    No Known Activations