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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating distance or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollo
    -0.17
    ãģĴ
    -0.16
    erson
    -0.16
    anan
    -0.15
    svc
    -0.15
    noch
    -0.14
    inger
    -0.14
    obus
    -0.14
    à¸Ńà¸ļ
    -0.14
    ador
    -0.14
    POSITIVE LOGITS
     concerned
    0.22
    FETCH
    0.20
     goes
    0.18
     apt
    0.18
     fetched
    0.18
    Concern
    0.16
     go
    0.15
    -go
    0.15
    /***/
    0.15
    eo
    0.15
    Act Density 0.005%

    No Known Activations