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

    Neuronpedia

    INDEX
    Explanations

    references to extraterrestrial beings or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to extraterrestrial beings or aliens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okers
    -0.91
    oker
    -0.83
    Ö¼
    -0.82
    soDeliveryDate
    -0.80
    YR
    -0.79
    heet
    -0.78
    arf
    -0.76
    theless
    -0.74
    hirt
    -0.73
    EY
    -0.71
    POSITIVE LOGITS
     abduction
    1.22
     abduct
    1.05
     invaders
    0.92
     invasion
    0.92
     visitation
    0.89
     civilizations
    0.89
    ware
    0.87
     species
    0.86
     spaceship
    0.84
     aliens
    0.82
    Act Density 0.022%

    No Known Activations