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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions or phrases indicating relationships in discussions about competitions or events in gaming and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Buk
    -0.80
     Berm
    -0.73
     Applicant
    -0.70
     Bundy
    -0.67
     Baghd
    -0.67
     mosqu
    -0.66
     Truck
    -0.66
     Mate
    -0.66
     Tile
    -0.65
     Goo
    -0.65
    POSITIVE LOGITS
    selves
    1.08
    theless
    1.06
    redients
    1.00
    ilogy
    0.92
    have
    0.90
    terday
    0.87
    ards
    0.83
    acters
    0.83
    fore
    0.83
    dated
    0.82
    Act Density 0.068%

    No Known Activations