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

    Neuronpedia

    INDEX
    Explanations

    the word "ghost" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to ghosts and ghost-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.86
    tics
    -0.76
    onian
    -0.75
    enegger
    -0.75
    unes
    -0.72
    Effective
    -0.69
    tical
    -0.68
    utherford
    -0.67
    utics
    -0.66
    nice
    -0.66
    POSITIVE LOGITS
    busters
    1.09
     haunting
    0.96
    writer
    0.95
    written
    0.94
    buster
    0.93
    writing
    0.88
    door
    0.83
    lla
    0.82
    writers
    0.79
    glass
    0.78
    Act Density 0.038%

    No Known Activations