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

    Neuronpedia

    INDEX
    Explanations

    references to humans and human-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strecke
    -0.40
    Біографія
    -0.37
     gối
    -0.36
    azgo
    -0.36
     boste
    -0.33
     vueltas
    -0.32
    IBOutlet
    -0.32
    ebbe
    -0.32
     vanguardia
    -0.32
     menetap
    -0.32
    POSITIVE LOGITS
     human
    4.13
     Human
    3.72
    Human
    3.70
    human
    3.69
     HUMAN
    3.34
    HUMAN
    3.23
     humans
    2.67
     humaine
    2.59
     humain
    2.59
     humano
    2.58
    Act Density 0.103%

    No Known Activations