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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize temporal context or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atta
    -0.15
    uraa
    -0.14
    313
    -0.14
    gether
    -0.14
    nee
    -0.14
    kk
    -0.14
     Porn
    -0.14
    -house
    -0.13
    314
    -0.13
    cai
    -0.13
    POSITIVE LOGITS
     best
    0.22
     odds
    0.22
    elic
    0.20
    -best
    0.20
     stake
    0.20
    (best
    0.19
    best
    0.19
     Odds
    0.18
     issue
    0.17
     minimum
    0.17
    Act Density 0.063%

    No Known Activations