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

    Neuronpedia

    INDEX
    Explanations

    verbs related to decision-making and responsibility

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

    Pronouns following verbs

    np_acts-logits-general · gemini-2.0-flash

    actions involving himself or his

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     him
    -1.62
    him
    -1.20
     Him
    -1.14
     ihn
    -0.94
     honom
    -0.93
    Him
    -0.85
     ihm
    -0.81
     Celui
    -0.75
     او
    -0.75
    He
    -0.73
    POSITIVE LOGITS
     himself
    1.60
     istrinya
    1.35
     his
    1.28
    himself
    1.28
    his
    0.97
     seinen
    0.95
     wife
    0.93
     consultato
    0.91
     himſelf
    0.89
     seine
    0.84
    Act Density 0.854%

    No Known Activations