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

    Neuronpedia

    INDEX
    Explanations

    references to human beings and aspects of human existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strecke
    -0.40
     boste
    -0.36
     respective
    -0.36
     kệ
    -0.35
     Besten
    -0.35
     treo
    -0.35
     spill
    -0.34
     parfüm
    -0.34
     Höhe
    -0.34
     specifico
    -0.34
    POSITIVE LOGITS
    Human
    1.41
    human
    1.36
     Human
    1.34
     human
    1.27
    HUMAN
    1.23
     HUMAN
    1.20
     Humans
    1.05
    Humans
    1.05
    humans
    1.02
     humans
    1.01
    Act Density 0.142%

    No Known Activations