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

    Neuronpedia

    INDEX
    Explanations

    expressions related to individuality and personal ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arto
    -0.19
    bart
    -0.16
    ija
    -0.15
    ocator
    -0.15
    -basket
    -0.14
    aro
    -0.14
    hlas
    -0.14
    FORE
    -0.14
     RuntimeObject
    -0.14
    ken
    -0.14
    POSITIVE LOGITS
     version
    0.20
     own
    0.19
     versions
    0.17
    version
    0.17
    subclass
    0.16
     Stability
    0.16
    WT
    0.15
     Moss
    0.15
    ome
    0.14
    _VERSION
    0.14
    Act Density 0.222%

    No Known Activations