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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing conjunctions or inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bubbles
    -0.16
    idy
    -0.15
     Gos
    -0.15
    å°½
    -0.15
     consec
    -0.14
    reon
    -0.14
     Birch
    -0.14
    itor
    -0.14
    akes
    -0.14
    ARC
    -0.13
    POSITIVE LOGITS
     etc
    0.17
     Hab
    0.15
    両
    0.15
    hots
    0.15
    398
    0.14
     ones
    0.14
    URN
    0.13
    lap
    0.13
    shan
    0.13
    ETHER
    0.13
    Act Density 0.092%

    No Known Activations