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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific location names, particularly related to military conflicts or geopolitical events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.91
    OGND
    -0.85
     ISNI
    -0.80
     Italijani
    -0.74
    PhysRevD
    -0.73
    GEBURTS
    -0.73
    Febru
    -0.72
     &___
    -0.71
    rungsseite
    -0.71
    GEBURTSDATUM
    -0.69
    POSITIVE LOGITS
     indescri
    1.40
     unspeak
    1.39
     shenan
    1.38
     apprehen
    1.38
     indestru
    1.35
     disagre
    1.35
     gaily
    1.34
     reluct
    1.29
     vainly
    1.26
     tolerably
    1.24
    Act Density 0.264%

    No Known Activations