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

    Neuronpedia

    INDEX
    Explanations

    references to books and reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippers
    -0.18
    ç¯ī
    -0.15
    ãĤĮãģ©
    -0.15
    zas
    -0.15
    usercontent
    -0.15
    itet
    -0.15
    adge
    -0.15
     Kron
    -0.15
    ANTA
    -0.15
    getti
    -0.14
    POSITIVE LOGITS
    worm
    0.25
     Depos
    0.25
    ends
    0.23
     traversal
    0.23
    ish
    0.21
    lover
    0.20
    stagram
    0.19
    store
    0.19
    wy
    0.18
     worms
    0.18
    Act Density 0.016%

    No Known Activations