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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completeness or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icl
    -0.16
    coli
    -0.16
    ãĥ¼ãĥĢ
    -0.14
    alis
    -0.14
    stm
    -0.13
    ugs
    -0.13
    ousands
    -0.13
     odst
    -0.13
    cliffe
    -0.13
    à¸Ļà¸Ń
    -0.13
    POSITIVE LOGITS
     all
    0.29
    =all
    0.25
     encompass
    0.24
     terrain
    0.23
    rou
    0.23
    uring
    0.22
     Terrain
    0.21
    (all
    0.21
    terrain
    0.21
    .all
    0.20
    Act Density 0.039%

    No Known Activations