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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various organizational missions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ture
    -0.17
    asan
    -0.15
    ApplicationContext
    -0.15
    elier
    -0.15
    ãĤ¤ãĤ¯
    -0.15
    /list
    -0.15
    asmus
    -0.14
    idence
    -0.14
    icts
    -0.14
    ì§Ī
    -0.14
    POSITIVE LOGITS
    naire
    0.23
    aries
    0.19
    erchant
    0.18
    atic
    0.16
    naires
    0.16
    avicon
    0.15
    omez
    0.14
    anova
    0.14
    hatt
    0.14
    ToF
    0.14
    Act Density 0.022%

    No Known Activations