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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recommendations or preferences in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obec
    -0.15
    aylor
    -0.15
    ynchronously
    -0.15
    .ep
    -0.14
    IM
    -0.14
    ime
    -0.14
    à¹Ĥà¸Ļ
    -0.14
    engin
    -0.13
    .sendStatus
    -0.13
    alted
    -0.13
    POSITIVE LOGITS
    otto
    0.18
     Gam
    0.16
    ovan
    0.16
    ãģijãĤĮãģ©
    0.15
    Äįer
    0.15
    .allocate
    0.15
    価
    0.15
    Gam
    0.15
    Å¡ak
    0.14
     appreciate
    0.14
    Act Density 0.048%

    No Known Activations