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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "brief" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hlen
    -0.17
    al
    -0.16
    ombo
    -0.16
    adol
    -0.15
    vro
    -0.15
    hed
    -0.15
    hausen
    -0.15
    aday
    -0.15
    thic
    -0.14
    ais
    -0.14
    POSITIVE LOGITS
    case
    0.36
    ings
    0.31
    cases
    0.26
    est
    0.25
    ness
    0.22
    ly
    0.21
    ening
    0.20
    Ļ¨
    0.20
    ens
    0.19
    INGS
    0.19
    Act Density 0.013%

    No Known Activations