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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing cognitive awareness or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ton
    -0.15
    put
    -0.15
    sg
    -0.15
    bers
    -0.14
    da
    -0.14
    ми
    -0.14
     Tun
    -0.14
    min
    -0.14
    over
    -0.14
    borne
    -0.14
    POSITIVE LOGITS
    Plug
    0.15
    ROKE
    0.15
    otton
    0.15
    ANNEL
    0.15
    plers
    0.15
    lemn
    0.15
    rank
    0.15
    ULK
    0.14
    _CFG
    0.14
    .dtd
    0.14
    Act Density 0.030%

    No Known Activations