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

    Neuronpedia

    INDEX
    Explanations

    words related to haunted locations or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to haunted locations or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyah
    -0.75
    iannopoulos
    -0.74
    ettel
    -0.73
    cellence
    -0.72
    utenberg
    -0.72
    ibaba
    -0.72
    enture
    -0.71
     NCT
    -0.70
    oulos
    -0.70
    weeney
    -0.69
    POSITIVE LOGITS
     haunted
    0.93
    crow
    0.92
     haunt
    0.88
     haun
    0.86
     Haunted
    0.85
     haunting
    0.84
    Haunted
    0.80
     Mansion
    0.78
    sight
    0.75
     attractions
    0.74
    Act Density 0.058%

    No Known Activations