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

    Neuronpedia

    INDEX
    Explanations

    sentence connectors and punctuation that indicate continuation or elaboration in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.21
     Houſe
    -1.10
     Reſ
    -1.10
     itſelf
    -1.08
    ſelf
    -1.07
    ſelves
    -1.07
     Efq
    -1.06
    neſs
    -1.06
     houſe
    -1.05
     myſelf
    -1.04
    POSITIVE LOGITS
    ，
    0.73
     but
    0.73
    and
    0.72
     ,
    0.71
    ),
    0.67
    ))
    0.66
    )
    0.65
     DRAWINGS
    0.64
    to
    0.64
    .
    0.63
    Act Density 0.087%

    No Known Activations