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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of leaving or departures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    leaving things behind or aside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.43
    BagLayout
    -0.43
    voerd
    -0.42
     DataTypes
    -0.41
    HKEY
    -0.41
    strerror
    -0.41
     réfé
    -0.41
    ísimo
    -0.41
    ModelAdmin
    -0.41
     trésor
    -0.40
    POSITIVE LOGITS
     Leave
    1.47
    Leave
    1.46
     leave
    1.44
    leave
    1.38
     leaving
    1.30
     Leaving
    1.30
    Leaving
    1.27
    leaving
    1.23
     LEAVE
    1.21
     leaves
    1.19
    Act Density 0.033%

    No Known Activations