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

    Neuronpedia

    INDEX
    Explanations

    references to events or gatherings and their organization details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "stop" or "stopping"

    np_acts-logits-general · gemini-2.0-flash

    stopping or stopping by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.81
     Jefus
    -0.78
    ſelves
    -0.76
     Efq
    -0.75
     fevere
    -0.75
     Cæsar
    -0.75
     Eſ
    -0.71
     Chriftian
    -0.70
     crdi
    -0.69
     Majefty
    -0.68
    POSITIVE LOGITS
     stop
    2.10
     Stop
    1.90
     stopping
    1.86
     stops
    1.84
    Stop
    1.81
    stop
    1.79
     stopped
    1.79
    stopped
    1.50
     Stopped
    1.50
    stopping
    1.50
    Act Density 0.172%

    No Known Activations