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

    Neuronpedia

    INDEX
    Explanations

    dialogue involving personal interactions and statements indicating actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.60
     Himo
    -0.52
     <>",
    -0.48
     Ansch
    -0.47
    κια
    -0.47
     pilote
    -0.46
    ̈́
    -0.46
     rider
    -0.45
     transferir
    -0.45
     roadside
    -0.45
    POSITIVE LOGITS
     entering
    1.18
     Entering
    1.14
     door
    1.13
     entered
    1.13
     entry
    1.12
     enters
    1.10
     enter
    1.10
    entering
    1.08
    Entering
    1.07
     knocking
    1.04
    Act Density 0.415%

    No Known Activations