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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     steep
    -0.62
     scarcity
    -0.60
     worn
    -0.58
     allowances
    -0.57
     heav
    -0.57
     commod
    -0.57
     mainline
    -0.57
     discriminating
    -0.56
     scra
    -0.56
     brace
    -0.55
    POSITIVE LOGITS
    icz
    1.19
    ovsky
    1.01
    akis
    0.97
    ois
    0.96
    ean
    0.96
    ansky
    0.95
    yk
    0.95
    ove
    0.94
    anski
    0.94
    aja
    0.94
    Act Density 1.971%

    No Known Activations