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

    Neuronpedia

    INDEX
    Explanations

    expressions that describe the ups and downs of experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMPL
    -0.18
    leine
    -0.16
    NSE
    -0.16
    заб
    -0.15
    ibt
    -0.15
    ÙĬتÙĬ
    -0.14
    _MODULES
    -0.14
    ãĥ¥ãĥ¼
    -0.14
    ungan
    -0.14
    ìĥģ
    -0.14
    POSITIVE LOGITS
     lows
    0.30
     downs
    0.27
     outs
    0.24
     Downs
    0.24
     cons
    0.21
     greens
    0.20
     highs
    0.19
    -outs
    0.19
    rets
    0.19
    ucs
    0.18
    Act Density 0.046%

    No Known Activations