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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts emphasizing the idea of "nothing" or the absence of value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erable
    -0.17
    ker
    -0.16
    abase
    -0.15
    ži
    -0.15
    lap
    -0.15
    XXXX
    -0.15
    sn
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    ying
    -0.14
    erli
    -0.14
    POSITIVE LOGITS
     short
    0.28
     less
    0.26
     SHORT
    0.23
     Short
    0.22
     menos
    0.20
    (short
    0.20
    Short
    0.20
    short
    0.19
    -short
    0.19
    hort
    0.18
    Act Density 0.021%

    No Known Activations