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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases involving quantities or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¯Ķè¼ĥ
    -0.15
    RIX
    -0.14
    stvo
    -0.14
    å°ij
    -0.14
    atro
    -0.14
     Nearly
    -0.14
    ÑŁ
    -0.14
    istrat
    -0.14
    gressor
    -0.13
    ä¹ħ
    -0.13
    POSITIVE LOGITS
     ideal
    0.27
     optimal
    0.23
     half
    0.23
     halfway
    0.23
     stellar
    0.22
    ideal
    0.21
     perfect
    0.20
     optimum
    0.20
     expected
    0.19
     Ideal
    0.19
    Act Density 0.022%

    No Known Activations