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

    Neuronpedia

    INDEX
    Explanations

    references to guests in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norris
    -0.55
    terung
    -0.54
    highway
    -0.53
     malpractice
    -0.53
     ols
    -0.52
     Whittaker
    -0.52
    forma
    -0.52
    ofsky
    -0.51
     verrez
    -0.51
     lätt
    -0.50
    POSITIVE LOGITS
     guest
    3.55
     guests
    3.47
     Guests
    3.29
     Guest
    3.28
     GUEST
    3.22
    Guest
    3.18
    guest
    3.13
    Guests
    3.11
    GUEST
    2.97
    guests
    2.92
    Act Density 0.036%

    No Known Activations