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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "Has" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.72
    ITERATURE
    -0.70
     tombé
    -0.68
     abandonné
    -0.67
    irited
    -0.66
    Bahnhof
    -0.66
    tyd
    -0.65
    playerName
    -0.63
    ffion
    -0.63
    lause
    -0.63
    POSITIVE LOGITS
     been
    0.61
    been
    0.61
     NSCoder
    0.54
     BEEN
    0.48
     browns
    0.47
    Been
    0.46
    had
    0.46
    Iden
    0.46
     fince
    0.44
     Leafs
    0.43
    Act Density 0.119%

    No Known Activations