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

    Neuronpedia

    INDEX
    Explanations

    repetitive occurrences of the word 'been' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.12
    DockStyle
    -0.96
     myſelf
    -0.93
     StringTokenizer
    -0.90
     Majefty
    -0.87
     houſe
    -0.86
     fevere
    -0.85
     Theſe
    -0.84
     avoient
    -0.84
     Roskov
    -0.83
    POSITIVE LOGITS
     been
    1.28
     was
    0.94
     has
    0.83
     is
    0.81
     Been
    0.78
    been
    0.77
     BEEN
    0.74
     previously
    0.69
     Was
    0.68
    HasBeen
    0.68
    Act Density 0.109%

    No Known Activations