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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "erasing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     insp
    -0.70
     Caval
    -0.62
    InjectMocks
    -0.60
     strut
    -0.59
     turi
    -0.58
    Gemeinden
    -0.57
    Jumbo
    -0.56
    quinone
    -0.56
    UDO
    -0.56
     propor
    -0.56
    POSITIVE LOGITS
     Er
    2.54
     er
    2.47
    Er
    2.44
     ER
    1.80
     Erm
    1.39
     Erskine
    1.28
     Eras
    1.26
     Eri
    1.20
    ER
    1.18
    Erm
    1.18
    Act Density 0.168%

    No Known Activations