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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to human nature and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kệ
    -0.38
    cocho
    -0.37
    retum
    -0.36
     Höhe
    -0.36
    zeg
    -0.35
     respective
    -0.35
    ท้าย
    -0.35
     distinción
    -0.35
     கி
    -0.35
    IKI
    -0.34
    POSITIVE LOGITS
    Human
    1.21
     Human
    1.16
    human
    1.13
    HUMAN
    1.05
     human
    1.05
     HUMAN
    0.97
     Humans
    0.94
    Humans
    0.94
     Manusia
    0.86
     uman
    0.85
    Act Density 0.108%

    No Known Activations