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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "brief" and related forms indicating shortness or conciseness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.15
     eventual
    -0.15
    iid
    -0.14
    ê¶Į
    -0.14
    plier
    -0.14
    802
    -0.14
    /is
    -0.14
    vation
    -0.13
     eventually
    -0.13
    ehler
    -0.13
    POSITIVE LOGITS
    case
    0.19
    ened
    0.17
    evin
    0.17
    /tiny
    0.17
    urb
    0.17
     (<
    0.16
    ening
    0.16
     جدا
    0.16
    sville
    0.16
    ty
    0.16
    Act Density 0.032%

    No Known Activations