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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decisions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anne
    -0.17
     Dien
    -0.15
    occo
    -0.15
    eks
    -0.14
    lashes
    -0.13
     reco
    -0.13
     sudden
    -0.13
    ÙĬÙĨا
    -0.13
    hek
    -0.13
     Puppet
    -0.13
    POSITIVE LOGITS
    icast
    0.18
    roj
    0.16
    .dtd
    0.15
     каÑĪ
    0.15
    BuilderInterface
    0.15
    ابت
    0.14
    Ultimately
    0.14
    ough
    0.14
    ylon
    0.14
    wij
    0.14
    Act Density 0.241%

    No Known Activations