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

    Neuronpedia

    INDEX
    Explanations

    terms related to stakeholder groups and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.70
    #
    -0.61
    ArgsConstructor
    -0.56
    loze
    -0.54
    gående
    -0.53
    jetunion
    -0.50
     yle
    -0.49
     ilma
    -0.49
     Normdatei
    -0.49
     grø
    -0.49
    POSITIVE LOGITS
     who
    1.00
     persons
    0.95
     whom
    0.90
     Persons
    0.88
     person
    0.81
     individuals
    0.80
    Individuals
    0.79
     Individuals
    0.77
    individuals
    0.75
    whom
    0.72
    Act Density 0.267%

    No Known Activations