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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improving and changing lives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     double
    -0.24
     Double
    -0.22
    double
    -0.22
    Double
    -0.19
     doubles
    -0.18
    DOUBLE
    -0.17
    -double
    -0.17
    _double
    -0.16
    (double
    -0.16
    (Double
    -0.16
    POSITIVE LOGITS
     lives
    0.96
     Lives
    0.77
     futures
    0.35
     hearts
    0.32
     life
    0.31
     жизни
    0.31
     minds
    0.30
     lifes
    0.29
    ives
    0.28
     live
    0.28
    Act Density 0.123%

    No Known Activations