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

    Neuronpedia

    INDEX
    Explanations

    keywords related to television shows or media productions

    oai_token-act-pair · gpt-3.5-turbo

    references to television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     solitary
    -0.68
     saline
    -0.63
     Aval
    -0.63
     STATES
    -0.62
     annexed
    -0.61
    illard
    -0.61
    illet
    -0.59
     Pastebin
    -0.59
     Nest
    -0.59
    ntil
    -0.58
    POSITIVE LOGITS
    biz
    1.58
    runners
    1.56
    runner
    1.50
    manship
    1.35
    mable
    1.17
    downs
    1.11
    room
    1.10
    case
    1.07
    rooms
    1.05
    girls
    1.03
    Act Density 0.045%

    No Known Activations