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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to rules, regulations, and standards

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to rules, authority, and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.81
    plet
    -0.78
    leys
    -0.67
    pron
    -0.67
     unden
    -0.66
    star
    -0.66
     glim
    -0.66
     Citiz
    -0.64
    ãĥĺ
    -0.64
     newcom
    -0.63
    POSITIVE LOGITS
     relating
    0.78
     ("
    0.69
     among
    0.69
     ('
    0.67
     between
    0.66
     regarding
    0.66
     (.
    0.66
    :(
    0.65
     ([
    0.64
     belonging
    0.64
    Act Density 0.219%

    No Known Activations