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

    Neuronpedia

    INDEX
    Explanations

    terms related to beauty treatments, particularly for eyelashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neck
    -0.17
    æ´
    -0.15
     mand
    -0.15
    awe
    -0.14
    ÙĨداÙĨ
    -0.14
    (DWORD
    -0.14
     Alice
    -0.14
    xmm
    -0.14
    ounsel
    -0.14
     jur
    -0.14
    POSITIVE LOGITS
     lash
    0.27
    lash
    0.27
     eyel
    0.26
     lashes
    0.26
     Ey
    0.26
     mascara
    0.25
    lashes
    0.23
     Eye
    0.23
    çĿ
    0.22
     eye
    0.21
    Act Density 0.016%

    No Known Activations