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

    Neuronpedia

    INDEX
    Explanations

    locations where someone arrives at or departs from

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and times of arrival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    criptions
    -0.65
    rand
    -0.61
    witch
    -0.61
    rat
    -0.61
     thirst
    -0.60
    ulating
    -0.60
    cription
    -0.60
    glass
    -0.59
     dealt
    -0.58
    shadow
    -0.58
    POSITIVE LOGITS
     shores
    0.94
    ctica
    0.77
     Arri
    0.75
     fray
    0.74
    ãĥ¯
    0.73
    INGTON
    0.72
     Medina
    0.72
     fruition
    0.70
    apolis
    0.70
     Aires
    0.70
    Act Density 0.150%

    No Known Activations