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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conſ
    -0.73
     myſelf
    -0.72
     pleaſure
    -0.67
     ſche
    -0.67
    ValueStyle
    -0.66
     itſelf
    -0.65
     ſever
    -0.64
     reaſon
    -0.61
     Perſ
    -0.61
    placement
    -0.60
    POSITIVE LOGITS
     es
    1.47
     sp
    0.91
     ddelweddau
    0.84
     Qu
    0.77
     е
    0.76
    '},
    0.74
    '],
    0.71
    '}>
    0.71
    '):
    0.70
    "],
    0.70
    Act Density 0.046%

    No Known Activations