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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "brief" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ê¶Į
    -0.16
    al
    -0.15
     Kaynak
    -0.14
     Rolled
    -0.14
    uele
    -0.14
    adol
    -0.13
    .optString
    -0.13
    GBK
    -0.13
     neither
    -0.13
    ceph
    -0.13
    POSITIVE LOGITS
    case
    0.20
    mente
    0.18
    ty
    0.17
    ening
    0.16
     (<
    0.16
    ened
    0.15
    ogue
    0.15
    .ly
    0.15
    sville
    0.15
    utin
    0.15
    Act Density 0.029%

    No Known Activations