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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vers
    -0.16
    etter
    -0.15
    laus
    -0.14
    ãģĩ
    -0.14
    amba
    -0.14
     optarg
    -0.14
    uer
    -0.14
    iller
    -0.14
    .DefaultCellStyle
    -0.14
    gan
    -0.13
    POSITIVE LOGITS
     existence
    0.19
    existence
    0.17
    Exist
    0.16
     Exist
    0.16
    олаг
    0.16
    ÏĦεÏį
    0.14
     ÙĪجÙĪد
    0.14
    Why
    0.14
    _exist
    0.14
    Exists
    0.14
    Act Density 0.057%

    No Known Activations