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

    Neuronpedia

    INDEX
    Explanations

    phrases related to shared experiences and common beliefs within communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remainder
    -0.20
    ضÙĦ
    -0.17
    ugi
    -0.16
    QA
    -0.15
    mons
    -0.14
    .schedulers
    -0.13
    chet
    -0.13
    ůst
    -0.13
    aten
    -0.13
    hiro
    -0.13
    POSITIVE LOGITS
     common
    0.76
     shared
    0.66
    common
    0.61
    shared
    0.59
     Common
    0.58
     COMMON
    0.54
    -common
    0.53
    Shared
    0.53
    Common
    0.52
     Shared
    0.51
    Act Density 0.184%

    No Known Activations