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

    Neuronpedia

    INDEX
    Explanations

    personal reflections and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atch
    -0.16
    atsu
    -0.16
    urette
    -0.15
     cheat
    -0.14
    406
    -0.14
    -hole
    -0.14
    inee
    -0.14
    iera
    -0.14
    .uc
    -0.14
    erialize
    -0.14
    POSITIVE LOGITS
     myself
    0.18
    rieb
    0.18
     mine
    0.17
    rane
    0.16
    atak
    0.15
     Wid
    0.15
     ours
    0.15
     personally
    0.14
    ataka
    0.14
    figcaption
    0.14
    Act Density 0.212%

    No Known Activations