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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jah
    -0.17
     Gh
    -0.16
     Jes
    -0.16
    avers
    -0.16
    itt
    -0.15
     spotted
    -0.14
    ila
    -0.14
     Rare
    -0.14
    (
    -0.14
    rew
    -0.13
    POSITIVE LOGITS
    ohan
    0.17
    criptors
    0.17
    arov
    0.15
    ancell
    0.15
    _OD
    0.14
    ovel
    0.14
    tails
    0.14
    ernity
    0.14
    antar
    0.14
    rž
    0.14
    Act Density 0.005%

    No Known Activations