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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "brief" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombo
    -0.18
    issen
    -0.18
    ais
    -0.18
    aises
    -0.14
    apro
    -0.14
    951
    -0.14
    érc
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    izado
    -0.14
    enga
    -0.13
    POSITIVE LOGITS
    case
    0.31
    cases
    0.22
    est
    0.19
    .ly
    0.18
    ness
    0.17
    s
    0.17
     (<
    0.16
    -lived
    0.16
    zeitig
    0.15
    ening
    0.15
    Act Density 0.022%

    No Known Activations