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

    Neuronpedia

    INDEX
    Explanations

    phrases related to titles, such as movie titles, book titles, or news article titles

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote connections or relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     superf
    -0.72
     arrivals
    -0.68
     chem
    -0.68
     aft
    -0.68
     concessions
    -0.67
     annexed
    -0.67
     strikers
    -0.67
     detriment
    -0.66
     breaker
    -0.66
     point
    -0.66
    POSITIVE LOGITS
    selves
    1.18
    itialized
    1.09
     Them
    1.08
     Us
    0.94
     Than
    0.88
     Its
    0.87
     Each
    0.87
     Himself
    0.85
    slaught
    0.84
     Their
    0.83
    Act Density 0.217%

    No Known Activations