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

    Neuronpedia

    INDEX
    Explanations

    instances of the abbreviation "DE" or related acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RNA
    -0.17
    зÑĮ
    -0.16
    êu
    -0.16
    DST
    -0.16
    RX
    -0.15
    ReturnValue
    -0.15
    ëĥ
    -0.15
    RN
    -0.14
    F
    -0.14
    RK
    -0.14
    POSITIVE LOGITS
    PARTMENT
    0.31
    PRECATED
    0.27
    POSIT
    0.26
    PLOY
    0.26
    LETED
    0.25
    GREE
    0.25
    SSERT
    0.25
    SKTOP
    0.24
    VICES
    0.24
    EP
    0.24
    Act Density 0.010%

    No Known Activations