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

    Neuronpedia

    INDEX
    Explanations

    attributes related to performance and consistency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -1.26
     betweenstory
    -1.08
    RegressionTest
    -0.96
    Personensuche
    -0.94
    sizeCache
    -0.93
     مشين
    -0.86
    oredCriteria
    -0.86
     propOrder
    -0.74
     تضيفلها
    -0.74
    StoryboardSegue
    -0.67
    POSITIVE LOGITS
    ness
    0.77
    NESS
    0.63
     enough
    0.63
    nesses
    0.53
    azin
    0.52
     geworden
    0.51
    hop
    0.49
    enough
    0.49
    PARED
    0.48
    itäts
    0.47
    Act Density 0.541%

    No Known Activations