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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and penal contexts

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

    Follows pronouns indicating people

    np_acts-logits-general · gemini-2.0-flash

    male pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fallu
    -0.90
     Theſe
    -0.83
     myſelf
    -0.81
     Anſ
    -0.81
    
    -0.80
     doubtnut
    -0.78
     Majefty
    -0.77
     Efq
    -0.77
     ſeveral
    -0.76
     itſelf
    -0.76
    POSITIVE LOGITS
     him
    2.64
     he
    2.04
     his
    1.69
    彼は
    1.61
     egli
    1.52
    him
    1.50
     ему
    1.49
     ihm
    1.48
    彼が
    1.43
     hänen
    1.37
    Act Density 1.153%

    No Known Activations