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

    Neuronpedia

    INDEX
    Explanations

    references to "Simple" concepts or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eenth
    -0.17
    402
    -0.15
    sel
    -0.15
    ngr
    -0.14
    leri
    -0.14
    esimal
    -0.14
    esco
    -0.14
    ãĥ³ãĤ°
    -0.14
    403
    -0.14
    ub
    -0.14
    POSITIVE LOGITS
    ton
    0.39
    tons
    0.37
    xes
    0.34
    -minded
    0.31
    TON
    0.27
    /simple
    0.26
     minded
    0.26
    ctic
    0.26
    st
    0.24
    /plain
    0.23
    Act Density 0.038%

    No Known Activations