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

    Neuronpedia

    INDEX
    Explanations

    references to individuals named "Robert."

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

    "Robert" followed by names/surnames

    np_acts-logits-general · gemini-2.0-flash

    Robert and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.94
    ſelves
    -0.72
     purpoſe
    -0.69
     greateſt
    -0.68
     pleaſure
    -0.68
     Italijanski
    -0.67
    HasAnnotation
    -0.66
     reaſon
    -0.66
    ſelf
    -0.65
     fevere
    -0.64
    POSITIVE LOGITS
    bie
    0.67
    Manbalar
    0.53
    bi
    0.52
     Bob
    0.49
    ble
    0.49
    би
    0.47
    ました
    0.44
    Bob
    0.44
    泊
    0.44
    oward
    0.44
    Act Density 0.091%

    No Known Activations