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

    Neuronpedia

    INDEX
    Explanations

    references to words and their usages in writing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ees
    -0.16
    beros
    -0.16
    eway
    -0.15
    yang
    -0.15
    åĨĨ
    -0.15
    dac
    -0.15
    imson
    -0.15
    λια
    -0.14
    ively
    -0.14
    quette
    -0.14
    POSITIVE LOGITS
    robe
    0.28
    mith
    0.27
    play
    0.27
    iness
    0.23
    processing
    0.22
     processor
    0.21
    processor
    0.21
    ings
    0.21
    ÙĨج
    0.20
     processors
    0.20
    Act Density 0.046%

    No Known Activations