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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the creation and development of projects or works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appropri
    -0.18
    lier
    -0.14
    Until
    -0.14
    uku
    -0.14
     duly
    -0.13
    ivers
    -0.13
    ERO
    -0.13
    ibe
    -0.13
    oley
    -0.13
    eyer
    -0.13
    POSITIVE LOGITS
     because
    0.25
     after
    0.22
     while
    0.21
     as
    0.20
     thanks
    0.19
     collabor
    0.18
     during
    0.18
    because
    0.18
     following
    0.18
     increment
    0.18
    Act Density 0.210%

    No Known Activations