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

    Neuronpedia

    INDEX
    Explanations

    questions around future events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unders
    -0.16
    chez
    -0.15
    ach
    -0.15
    enga
    -0.14
    trap
    -0.14
    vecs
    -0.14
    late
    -0.14
    pie
    -0.14
    antic
    -0.14
    .hs
    -0.14
    POSITIVE LOGITS
    ayo
    0.17
    imat
    0.15
    /how
    0.15
    lore
    0.14
     disposition
    0.14
    ards
    0.14
    owo
    0.14
    ยว
    0.14
     OPTIONS
    0.13
     upon
    0.13
    Act Density 0.133%

    No Known Activations