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

    Neuronpedia

    INDEX
    Explanations

    references to legal or ownership matters regarding property

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

    Returned, seized, stolen, lost, belonging, pilfered

    np_acts-logits-general · gemini-2.0-flash

    property stolen or returned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.65
     queſta
    -0.61
    ſelf
    -0.61
     itſelf
    -0.57
    makeConstraints
    -0.57
    WriteAttribute
    -0.57
    <unused68>
    -0.56
    ſelves
    -0.56
    <unused41>
    -0.56
    [@BOS@]
    -0.56
    POSITIVE LOGITS
     stolen
    0.42
     returned
    0.41
     lost
    0.40
    stolen
    0.37
    returned
    0.36
    lost
    0.34
     LOST
    0.33
     confiscated
    0.33
     ownership
    0.32
    垢
    0.31
    Act Density 0.291%

    No Known Activations