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

    Neuronpedia

    INDEX
    Explanations

    descriptions of creative projects and renovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     åĸ
    -0.17
    logan
    -0.14
    елов
    -0.14
     Contrast
    -0.13
     selfish
    -0.13
    adx
    -0.13
    ìŀIJ기
    -0.13
    roi
    -0.13
    081
    -0.12
    nar
    -0.12
    POSITIVE LOGITS
     authentic
    0.42
     faithful
    0.41
     accurate
    0.40
     auth
    0.38
     Authentic
    0.38
    Auth
    0.37
     authenticity
    0.37
     accurately
    0.36
    auth
    0.36
    -auth
    0.36
    Act Density 0.231%

    No Known Activations