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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to mandates and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cial
    -0.16
    741
    -0.16
    ertz
    -0.16
    érique
    -0.15
    üssen
    -0.15
    formed
    -0.14
    	Copyright
    -0.14
    ongo
    -0.14
    ansi
    -0.14
     Volk
    -0.14
    POSITIVE LOGITS
    ATORY
    0.24
    arin
    0.20
     Mand
    0.19
    loi
    0.17
    atory
    0.17
     mand
    0.17
    elson
    0.16
    itory
    0.16
    eps
    0.16
    ev
    0.16
    Act Density 0.009%

    No Known Activations