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

    Neuronpedia

    INDEX
    Explanations

    terms related to reduction or decreases in quantity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emoc
    -0.16
    inea
    -0.15
    iaÅĤ
    -0.14
    ocene
    -0.14
    Coeff
    -0.14
     fats
    -0.14
    ÙĨدر
    -0.13
    yonel
    -0.13
    RK
    -0.13
     Gratis
    -0.13
    POSITIVE LOGITS
    ening
    0.21
    eren
    0.20
    eref
    0.16
    ere
    0.16
    -than
    0.15
    ened
    0.15
    /no
    0.15
    ERE
    0.15
    mate
    0.15
    _than
    0.14
    Act Density 0.027%

    No Known Activations