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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to annotation or labeling in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ
    -0.16
    ney
    -0.15
     nug
    -0.15
    dra
    -0.15
    tery
    -0.14
    hausen
    -0.14
    hti
    -0.14
    NEY
    -0.14
    /lo
    -0.14
    eners
    -0.14
    POSITIVE LOGITS
    enties
    0.17
    еÑģÑĤва
    0.16
    ste
    0.15
     Pers
    0.15
    REFERRED
    0.15
    etch
    0.15
    coc
    0.15
    ä¹ħ
    0.14
     porr
    0.14
    nearest
    0.14
    Act Density 0.005%

    No Known Activations