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

    Neuronpedia

    INDEX
    Explanations

    mentions of someone leaving a specific place or situation

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases involving the word "the" and its context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rand
    -0.81
    JR
    -0.77
    agu
    -0.71
    VERSION
    -0.71
    »Ĵ
    -0.70
    yo
    -0.69
     Cosponsors
    -0.69
    GUI
    -0.68
    nav
    -0.67
    rg
    -0.67
    POSITIVE LOGITS
     confines
    1.05
     remainder
    1.03
     premises
    0.91
     scene
    0.90
     shores
    0.90
     town
    0.89
     door
    0.89
     bounds
    0.88
     entirety
    0.88
     country
    0.88
    Act Density 0.080%

    No Known Activations