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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prior notification or preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     minY
    -0.40
     HomeScreen
    -0.38
     rav
    -0.38
     impea
    -0.37
     aufs
    -0.36
     anticor
    -0.36
    Civi
    -0.36
     postIndex
    -0.36
     resultCode
    -0.35
    oudoune
    -0.35
    POSITIVE LOGITS
     advance
    1.06
    advance
    0.81
     ADVANCE
    0.73
     Advance
    0.73
    Advance
    0.71
     antemano
    0.70
    SourceChecksum
    0.67
    帖最后由
    0.56
     quietly
    0.53
    queryInterface
    0.52
    Act Density 0.067%

    No Known Activations