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

    Neuronpedia

    INDEX
    Explanations

    specific technological terms and product names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     conflicted
    -0.60
     toler
    -0.59
     ----------------------------------------------------------------
    -0.59
    />
    -0.58
     juggling
    -0.57
     %%
    -0.57
    ====
    -0.56
     hostile
    -0.55
     paradox
    -0.55
    ...?
    -0.55
    POSITIVE LOGITS
    senal
    0.77
    çİĭ
    0.69
    iann
    0.66
    è£ħ
    0.66
    shire
    0.64
     XIV
    0.64
    ²¾
    0.64
     Spa
    0.63
    XX
    0.62
    undy
    0.62
    Act Density 0.174%

    No Known Activations