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

    Neuronpedia

    INDEX
    Explanations

    words related to quarantine and guarantee

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quarantine and vaccination policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FUL
    -0.77
     MacArthur
    -0.67
    CHR
    -0.67
    ¿½
    -0.65
    CVE
    -0.62
    £ı
    -0.60
    GY
    -0.60
     incred
    -0.60
     fabrication
    -0.60
     comprehension
    -0.60
    POSITIVE LOGITS
    arant
    1.12
    ormal
    0.96
    ined
    0.94
    ulas
    0.92
    arding
    0.92
    ees
    0.90
    eed
    0.90
    inated
    0.88
    ula
    0.87
    inal
    0.86
    Act Density 0.010%

    No Known Activations