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

    Neuronpedia

    INDEX
    Explanations

    references to specific films and their creators

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

    before "burg", "Driver", "War", or "Time"

    np_acts-logits-general · gemini-2.0-flash

    Taxi Driver, Warburg, Dateline, WikiLeaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.95
     
    -0.83
    .
    -0.82
     in
    -0.80
     a
    -0.76
     the
    -0.75
    :
    -0.73
     and
    -0.72
     to
    -0.69
     on
    -0.69
    POSITIVE LOGITS
     ſever
    1.05
     Houſe
    1.02
     houſe
    1.01
    ſelves
    0.96
     itſelf
    0.96
     Perſ
    0.94
     ſche
    0.93
    CloseOperation
    0.92
     étoient
    0.91
    Personendaten
    0.91
    Act Density 1.717%

    No Known Activations