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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" and its connections to other phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tuttle
    -0.65
     incomplète
    -0.63
     ratify
    -0.59
     synchronize
    -0.58
     Администра
    -0.57
     bruise
    -0.57
     shave
    -0.57
     بک
    -0.57
     بگ
    -0.55
     Played
    -0.55
    POSITIVE LOGITS
     doing
    1.00
     playing
    0.98
     eating
    0.97
     researching
    0.95
     practicing
    0.94
     watching
    0.92
     picking
    0.92
     designing
    0.92
     buying
    0.91
     getting
    0.91
    Act Density 0.372%

    No Known Activations