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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.68
    henswürdigkeiten
    -0.54
     personer
    -0.49
     meisjes
    -0.49
    addCriterion
    -0.49
     vrouwen
    -0.49
    Individuals
    -0.48
    persons
    -0.47
     individuals
    -0.47
    scribers
    -0.45
    POSITIVE LOGITS
     fellow
    1.67
     colleagues
    1.38
    fellow
    1.36
     colleague
    1.32
    Fellow
    1.30
     peers
    1.28
     Fellow
    1.24
     FELLOW
    1.21
     collega
    1.19
     peer
    1.08
    Act Density 0.384%

    No Known Activations