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

    Neuronpedia

    INDEX
    Explanations

    words related to imposing laws, regulations, or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enforcement and regulation measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppers
    -0.68
    olitics
    -0.67
    iliate
    -0.66
    clerosis
    -0.66
    orage
    -0.66
    ãĥĺ
    -0.66
    hack
    -0.63
    estyles
    -0.63
    NL
    -0.62
    rosis
    -0.62
    POSITIVE LOGITS
     imposing
    3.24
     arresting
    1.98
     punishing
    1.90
     inviting
    1.78
     intimidating
    1.74
     engaging
    1.53
     commanding
    1.50
     defining
    1.50
     striking
    1.40
     discriminating
    1.39
    Act Density 0.043%

    No Known Activations