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

    Neuronpedia

    INDEX
    Explanations

    numerical representations of quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oods
    -0.17
    инки
    -0.16
    urons
    -0.16
    apes
    -0.15
    flows
    -0.15
    rades
    -0.15
    uling
    -0.15
    ulas
    -0.14
    illions
    -0.14
    inton
    -0.14
    POSITIVE LOGITS
     person
    0.24
    member
    0.20
     member
    0.19
    fold
    0.19
    person
    0.19
    -member
    0.18
    -person
    0.18
    :item
    0.18
     dimensional
    0.17
     Person
    0.17
    Act Density 0.128%

    No Known Activations