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

    Neuronpedia

    INDEX
    Explanations

    obituaries containing detailed information about individuals' lives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.29
     align
    -0.68
    <?
    -0.67
     attract
    -0.67
     prevent
    -0.66
    <?
    -0.66
     seek
    -0.65
     keep
    -0.64
    ⓧ
    -0.63
     continue
    -0.63
    POSITIVE LOGITS
     rafra
    1.59
     véhic
    1.57
     ftu
    1.44
     vété
    1.42
     »>
    1.41
     ?...
    1.41
     délib
    1.39
     accla
    1.37
     écout
    1.36
     soulign
    1.35
    Act Density 0.560%

    No Known Activations