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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagHelpers
    -0.83
     "").
    -0.70
     '').
    -0.69
    warded
    -0.68
     ")");
    -0.66
     "");
    -0.65
     "")
    -0.64
     Kie
    -0.64
    ouard
    -0.64
    ridged
    -0.64
    POSITIVE LOGITS
     person
    3.12
     Person
    2.93
    person
    2.86
    Person
    2.79
     PERSON
    2.74
    PERSON
    2.46
     Persons
    2.33
     persons
    2.30
    Persons
    2.22
    persons
    2.20
    Act Density 0.041%

    No Known Activations