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

    Neuronpedia

    INDEX
    Explanations

    names and words related to notable individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.77
    nesday
    -0.65
    urrencies
    -0.64
    auga
    -0.59
     horr
    -0.57
    retty
    -0.56
     hover
    -0.55
    nown
    -0.55
    itiveness
    -0.54
     inver
    -0.54
    POSITIVE LOGITS
    oise
    0.74
    ãĥķãĤ©
    0.69
    Adventure
    0.68
    ibrary
    0.68
    ãĥĥãĥī
    0.67
    ictionary
    0.66
    azeera
    0.65
    aida
    0.64
     Edison
    0.64
    Clock
    0.63
    Act Density 2.761%

    No Known Activations