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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nine
    -0.51
     Replies
    -0.51
    MaxValue
    -0.50
    Breaker
    -0.49
     Breen
    -0.48
     hefyd
    -0.48
     Shield
    -0.48
    eak
    -0.46
    ριν
    -0.46
     Bial
    -0.45
    POSITIVE LOGITS
    RegistryLite
    0.70
    ButterKnife
    0.63
    ViewImports
    0.59
     ModelExpression
    0.53
    Hentet
    0.52
    utentic
    0.52
    ParallelGroup
    0.50
    mità
    0.50
    readObject
    0.50
     acquit
    0.49
    Act Density 0.546%

    No Known Activations