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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate inherent or intrinsic qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dek
    -0.15
    าà¸ĩ
    -0.15
    ow
    -0.14
    ÑįÑĦ
    -0.14
    arde
    -0.13
    esters
    -0.13
    erp
    -0.13
    ard
    -0.13
    intern
    -0.13
     DEA
    -0.13
    POSITIVE LOGITS
    aniel
    0.15
    966
    0.14
    574
    0.14
    ANJI
    0.14
    644
    0.14
    ponge
    0.14
    ÑĮÑİ
    0.14
    594
    0.14
    744
    0.14
     vej
    0.14
    Act Density 0.009%

    No Known Activations