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

    Neuronpedia

    INDEX
    Explanations

    words related to international conflicts and events

    oai_token-act-pair · gpt-3.5-turbo

    proper names or identifiers related to organizations, potentially military or governmental

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gra
    -0.78
     bart
    -0.78
     introdu
    -0.76
    assetsadobe
    -0.75
     ende
    -0.74
     ancest
    -0.74
     Aly
    -0.73
     chants
    -0.73
     Tall
    -0.72
     cher
    -0.72
    POSITIVE LOGITS
    CS
    1.37
    FP
    1.35
    ISA
    1.34
    ND
    1.34
    RC
    1.32
    BS
    1.31
    MS
    1.31
    DS
    1.30
    TS
    1.30
    DP
    1.30
    Act Density 0.146%

    No Known Activations