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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acquiring knowledge or education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AW
    -0.16
    e
    -0.15
    /to
    -0.15
    och
    -0.14
    upro
    -0.14
    SM
    -0.14
     libertine
    -0.13
    AWN
    -0.13
    allon
    -0.13
    luk
    -0.13
    POSITIVE LOGITS
     about
    0.19
     Gover
    0.17
     depos
    0.15
    skirts
    0.15
    ’ta
    0.15
    ldb
    0.15
    ntax
    0.15
    OffsetTable
    0.15
     how
    0.15
    rys
    0.15
    Act Density 0.033%

    No Known Activations