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

    Neuronpedia

    INDEX
    Explanations

    academic and logical terms related to proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rego
    -0.17
    ort
    -0.17
     ed
    -0.16
     Vice
    -0.14
    ensi
    -0.14
     cent
    -0.14
    rops
    -0.14
    åĽłæѤ
    -0.13
    erset
    -0.13
    avis
    -0.13
    POSITIVE LOGITS
    adows
    0.15
     strate
    0.15
     Preis
    0.15
     Offices
    0.14
    mp
    0.14
    abel
    0.14
    ebek
    0.14
    apon
    0.14
    μβ
    0.14
    ivating
    0.14
    Act Density 0.340%

    No Known Activations