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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases that indicate belonging or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PYX
    -0.74
     Jefus
    -0.74
     fevere
    -0.67
     Majefty
    -0.64
    ValueStyle
    -0.64
     ✭✭
    -0.63
     itſelf
    -0.62
     Shakspeare
    -0.62
     Chriftian
    -0.61
     onlyOwner
    -0.61
    POSITIVE LOGITS
    OutOf
    0.78
     whack
    0.74
     outta
    0.72
     the
    0.66
     touch
    0.65
     reach
    0.64
     bounds
    0.63
     nowhere
    0.63
     context
    0.62
    ">)</
    0.62
    Act Density 0.054%

    No Known Activations