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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eunice
    -0.81
     perfons
    -0.73
     acreditar
    -0.72
     Roanoke
    -0.72
     Erskine
    -0.71
     forze
    -0.70
    ſelf
    -0.69
     Leith
    -0.69
     Woodford
    -0.69
     Raiders
    -0.69
    POSITIVE LOGITS
     been
    1.41
     has
    1.19
     had
    1.14
     have
    1.08
    ve
    0.95
     Has
    0.92
     Have
    0.85
     Audiodateien
    0.82
     ive
    0.82
     Ive
    0.82
    Act Density 0.075%

    No Known Activations