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

    Neuronpedia

    INDEX
    Explanations

    references to arts and cultural reviews or critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stras
    -0.15
    alem
    -0.15
    anut
    -0.14
    sr
    -0.14
    USTER
    -0.14
     tieten
    -0.14
     Bureau
    -0.14
    atomic
    -0.13
    zÄħd
    -0.13
     YORK
    -0.13
    POSITIVE LOGITS
    von
    0.16
    olls
    0.15
    kv
    0.15
    quip
    0.15
    dings
    0.15
    ock
    0.15
     reb
    0.14
    EFA
    0.14
    ajan
    0.14
    öh
    0.14
    Act Density 0.004%

    No Known Activations