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

    Neuronpedia

    INDEX
    Explanations

    instances of formal address and respectful titles in dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.69
    __':
    -0.61
    таратура
    -0.60
    AndEndTag
    -0.60
    AsUp
    -0.60
    ;*/
    -0.59
    '])){
    -0.58
    ])){
    -0.58
    ']))
    -0.58
    DockStyle
    -0.58
    POSITIVE LOGITS
     Vikipedi
    0.56
    Abp
    0.53
    DeleteBehavior
    0.50
    Flow
    0.49
    he
    0.48
    ضى
    0.47
    Geografi
    0.46
    getDisplay
    0.45
     Entrée
    0.45
    bek
    0.44
    Act Density 0.141%

    No Known Activations