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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the concept of something being completed or finished

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osity
    -0.70
     Forward
    -0.63
    resy
    -0.62
     associates
    -0.61
     partName
    -0.61
    oS
    -0.60
    yssey
    -0.60
    ãĥı
    -0.59
    iosity
    -0.59
     Galactic
    -0.56
    POSITIVE LOGITS
    kill
    1.20
    blown
    1.19
    rated
    1.08
    stated
    1.07
    loading
    1.01
    reaching
    0.99
    priced
    0.98
    drive
    0.97
    whelming
    0.96
    cast
    0.94
    Act Density 0.015%

    No Known Activations