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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.96
     autorytatywna
    -0.91
    TagMode
    -0.86
     GenerationType
    -0.81
     CreateTagHelper
    -0.80
    Autoritní
    -0.78
    IntoConstraints
    -0.76
    AddTagHelper
    -0.75
    ValueStyle
    -0.74
    verwijspagina
    -0.73
    POSITIVE LOGITS
     colleagues
    0.68
     friends
    0.64
     partners
    0.63
     colleague
    0.61
     acquaintances
    0.61
    friends
    0.60
     neighbors
    0.60
     classmates
    0.59
     neighbours
    0.58
     rivals
    0.58
    Act Density 0.338%

    No Known Activations