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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing existence or longevity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OLA
    -0.16
    okes
    -0.16
    ÃŃch
    -0.15
    оÑĢаз
    -0.15
    ocus
    -0.15
    exels
    -0.15
    ãĥ¼ãĥį
    -0.14
    ayne
    -0.14
    ONO
    -0.14
     ún
    -0.14
    POSITIVE LOGITS
     existed
    0.32
     since
    0.30
     exist
    0.27
     existence
    0.27
     exists
    0.24
     Since
    0.24
    since
    0.23
    åŃĺåľ¨
    0.23
     Exist
    0.21
    Since
    0.21
    Act Density 0.181%

    No Known Activations