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

    Neuronpedia

    INDEX
    Explanations

    names of specific organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various international organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ½
    -0.81
    espie
    -0.80
    posed
    -0.70
    ãĤ¨ãĥ«
    -0.70
    ties
    -0.69
    req
    -0.69
    +++
    -0.68
    adows
    -0.68
    ãĥ©ãĥ³
    -0.67
    iour
    -0.67
    POSITIVE LOGITS
     Organization
    1.05
     Organisation
    0.96
     XIII
    0.90
    eers
    0.82
     Confederation
    0.81
    acion
    0.79
     Arms
    0.76
     Headquarters
    0.74
    ally
    0.73
     Convention
    0.71
    Act Density 0.014%

    No Known Activations