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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms relating to specific population groups and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orman
    -0.16
    iyon
    -0.15
     Tony
    -0.14
    eck
    -0.14
    raph
    -0.13
    14
    -0.13
     pand
    -0.13
     Else
    -0.13
     Fu
    -0.13
    strup
    -0.13
    POSITIVE LOGITS
    hread
    0.16
    ibold
    0.15
    oric
    0.15
    reau
    0.15
    bast
    0.15
    à¸ģร
    0.15
    ambah
    0.15
    oles
    0.15
    hm
    0.14
    orz
    0.14
    Act Density 0.132%

    No Known Activations