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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to civilization and related concepts such as civility and annexation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to civility and civil affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prints
    -0.87
    horn
    -0.75
    velength
    -0.68
    iffe
    -0.67
     Parallel
    -0.66
     association
    -0.66
    hops
    -0.66
     takeaway
    -0.65
    print
    -0.65
    ploma
    -0.65
    POSITIVE LOGITS
    ility
    1.25
    ilities
    1.04
    itas
    0.95
    vy
    0.94
    ili
    0.86
    iencies
    0.85
    ould
    0.83
    auld
    0.82
    itational
    0.82
    ically
    0.81
    Act Density 0.018%

    No Known Activations