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

    Neuronpedia

    INDEX
    Explanations

    references to guests and their interactions in a dining or hosting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    being a guest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.48
     indietro
    -0.47
     Farley
    -0.44
     correto
    -0.43
     Horton
    -0.43
     Nicolai
    -0.43
    ************
    -0.43
    Mantenimiento
    -0.43
     Blackburn
    -0.42
    SuppressLint
    -0.42
    POSITIVE LOGITS
    Guest
    1.11
     Guest
    1.10
    guest
    1.09
     guest
    1.05
     GUEST
    1.01
    GUEST
    0.98
     Guests
    0.94
    Guests
    0.93
    guests
    0.93
     guests
    0.92
    Act Density 0.004%

    No Known Activations