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

    Neuronpedia

    INDEX
    Explanations

    document structure markers and indicators for sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.73
    PhysRev
    -0.67
     jScrollPane
    -0.66
    contentLoaded
    -0.64
    ंदीखरीदारी
    -0.62
    fieras
    -0.62
     parseFrom
    -0.61
    InvalidProtocol
    -0.61
    TestingModule
    -0.60
    __.__
    -0.59
    POSITIVE LOGITS
     should
    0.70
     Should
    0.60
    ibility
    0.57
    should
    0.55
     ability
    0.55
     can
    0.54
     Can
    0.53
    能否
    0.52
    Should
    0.51
     when
    0.51
    Act Density 0.069%

    No Known Activations