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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sanctimonious behavior

    oai_token-act-pair · gpt-3.5-turbo

    words related to sacrificial or ceremonial aspects of relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     taps
    -0.65
     root
    -0.65
     dangerously
    -0.64
     stack
    -0.63
     stroke
    -0.62
     ignition
    -0.62
     Swed
    -0.62
     solder
    -0.60
     tapped
    -0.60
     wave
    -0.59
    POSITIVE LOGITS
    imon
    5.13
    imony
    2.20
    amon
    1.21
    imi
    1.19
    iann
    1.14
    omon
    1.04
    aimon
    1.03
    imens
    1.02
    imaru
    1.00
    ime
    0.99
    Act Density 0.014%

    No Known Activations