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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate legal or formal appointments and relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     focus
    -0.50
    art
    -0.47
     
    -0.47
     &
    -0.45
    athen
    -0.43
     targeted
    -0.42
    ruhe
    -0.42
    brink
    -0.41
     form
    -0.40
     Clear
    -0.40
    POSITIVE LOGITS
    __);
    0.88
     Мексичка
    0.88
    transQ
    0.84
     AssemblyCulture
    0.80
    fjspx
    0.80
     autorytatywna
    0.79
    脚注の使い方
    0.77
    migrationBuilder
    0.75
     GenerationType
    0.75
     mergeFrom
    0.75
    Act Density 0.005%

    No Known Activations