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

    Neuronpedia

    INDEX
    Explanations

    mention or references to ghosts

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the term "ghost"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.79
    Effective
    -0.70
    tics
    -0.70
    onian
    -0.66
    enegger
    -0.66
    tical
    -0.64
    ventions
    -0.63
    oulos
    -0.62
    YC
    -0.59
     percentile
    -0.59
    POSITIVE LOGITS
    busters
    1.15
    buster
    1.10
    writer
    0.99
    written
    0.92
    writing
    0.88
     haunting
    0.86
    ly
    0.85
    door
    0.83
    liness
    0.80
    writers
    0.80
    Act Density 0.049%

    No Known Activations