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

    Neuronpedia

    INDEX
    Explanations

    fractions or ratios related to quantities or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morse
    -0.17
    ersh
    -0.15
    677
    -0.15
    cgi
    -0.15
    iske
    -0.14
     cabo
    -0.14
    eli
    -0.14
    =Value
    -0.14
     Garner
    -0.13
    irts
    -0.13
    POSITIVE LOGITS
    usan
    0.18
    imple
    0.15
    æīįèĥ½
    0.15
     tụ
    0.15
    [of
    0.14
    .easing
    0.14
     ç¯
    0.14
    conds
    0.14
    agg
    0.14
    عاÙĨ
    0.14
    Act Density 0.009%

    No Known Activations