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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values, particularly those representing quantities or distances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.07
    7:0.07
    8:0.06
    9:0.09
    10:0.10
    11:0.09
    Negative Logits
     itch
    -1.68
    Laughs
    -1.67
     loneliness
    -1.61
    staking
    -1.59
     xp
    -1.55
    quickShipAvailable
    -1.53
     gloom
    -1.52
     nausea
    -1.50
     mileage
    -1.49
    �
    -1.48
    POSITIVE LOGITS
    adr
    1.88
    ��
    1.77
    onomic
    1.69
    anes
    1.68
    mitter
    1.67
    ogi
    1.62
    prototype
    1.62
    �
    1.61
    icultural
    1.61
    addy
    1.60
    Act Density 0.000%

    No Known Activations