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

    Neuronpedia

    INDEX
    Explanations

    phrases related to television shows

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific TV show

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     solitary
    -0.75
    illard
    -0.68
    illet
    -0.65
     annexed
    -0.65
     saline
    -0.63
     Lucia
    -0.62
     steel
    -0.61
     reef
    -0.61
     STATES
    -0.60
     Aval
    -0.60
    POSITIVE LOGITS
    runners
    1.68
    biz
    1.62
    runner
    1.56
    manship
    1.36
    downs
    1.25
    room
    1.13
    case
    1.12
    mable
    1.12
    rooms
    1.06
    cases
    1.05
    Act Density 0.045%

    No Known Activations