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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency and positivity in behaviors or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inker
    -0.17
    оÑĤа
    -0.15
    \common
    -0.14
    lili
    -0.14
     Landing
    -0.14
    KNOWN
    -0.14
     ayn
    -0.14
    tron
    -0.13
    TemplateName
    -0.13
    æº
    -0.13
    POSITIVE LOGITS
    IFO
    0.14
    rique
    0.14
     Serge
    0.14
    edor
    0.14
    idth
    0.13
     Bound
    0.13
    oped
    0.13
     bound
    0.13
     spraw
    0.13
    Fo
    0.13
    Act Density 0.035%

    No Known Activations