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

    Neuronpedia

    INDEX
    Explanations

    expressions of time or duration in personal experiences

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

    Preceding "been" and related to time

    np_acts-logits-general · gemini-2.0-flash

    states that have been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     becauſe
    -0.90
     houſe
    -0.87
     myſelf
    -0.87
     Diſ
    -0.85
     whoſe
    -0.85
     ſtate
    -0.85
     purpoſe
    -0.84
     Efq
    -0.84
     Jefus
    -0.83
     itſelf
    -0.82
    POSITIVE LOGITS
     been
    0.84
     lama
    0.69
    ?");
    0.67
    %");
    0.67
    '])->
    0.67
    ")->
    0.62
    ?».
    0.61
    ')->
    0.60
     previously
    0.60
    )}$.
    0.59
    Act Density 0.144%

    No Known Activations