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

    Neuronpedia

    INDEX
    Explanations

    words related to reports and documentation of changes or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chner
    -0.16
    quete
    -0.16
    onis
    -0.16
    oot
    -0.16
    ixel
    -0.15
     Lopez
    -0.14
     Piece
    -0.14
    andal
    -0.13
    ibal
    -0.13
    ickey
    -0.13
    POSITIVE LOGITS
    WebResponse
    0.14
    HEMA
    0.14
    è±Ĭ
    0.14
    ãĤĵãģ©
    0.14
    arten
    0.14
    Launcher
    0.14
    ardy
    0.14
    alin
    0.14
    uros
    0.14
    ffen
    0.13
    Act Density 0.012%

    No Known Activations