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

    Neuronpedia

    INDEX
    Explanations

    references to individuals who are featured as guests

    oai_token-act-pair · gpt-3.5-turbo

    references to guest appearances or guest roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.73
     conflic
    -0.71
    erella
    -0.70
    cale
    -0.69
    hemat
    -0.68
    ooks
    -0.67
     Rite
    -0.67
     Skydragon
    -0.67
    tics
    -0.64
    yth
    -0.63
    POSITIVE LOGITS
     guests
    0.80
    visor
    0.78
     guest
    0.77
    Guest
    0.77
    staff
    0.76
    itors
    0.75
    ele
    0.74
    lift
    0.74
    roach
    0.74
     host
    0.73
    Act Density 0.035%

    No Known Activations