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

    Neuronpedia

    INDEX
    Explanations

    instances of commands or orders in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beck
    -0.20
    ucht
    -0.17
    ìķķ
    -0.15
    ecta
    -0.14
    isel
    -0.14
    æī¬
    -0.14
    λλ
    -0.14
    foil
    -0.14
    eam
    -0.13
     NavParams
    -0.13
    POSITIVE LOGITS
    atica
    0.16
    _UNS
    0.15
    ippet
    0.14
     immediate
    0.14
    enberg
    0.14
     subordinate
    0.14
    à¹ĥห
    0.14
    strar
    0.14
    agram
    0.14
    bian
    0.13
    Act Density 0.070%

    No Known Activations