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

    Neuronpedia

    INDEX
    Explanations

    historical references and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tan
    -0.78
    uana
    -0.76
    adin
    -0.76
    cheon
    -0.73
    utterstock
    -0.70
    zip
    -0.68
    chens
    -0.66
    pher
    -0.66
    achment
    -0.65
    iant
    -0.64
    POSITIVE LOGITS
     preservation
    0.92
     nostalg
    0.91
     record
    0.89
     Record
    0.84
     memories
    0.82
     remem
    0.82
     relics
    0.79
     Echoes
    0.79
     commem
    0.78
     eras
    0.77
    Act Density 4.512%

    No Known Activations