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

    Neuronpedia

    INDEX
    Explanations

    technical terms and functions related to programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢаÑĤи
    -0.15
    ries
    -0.15
     norge
    -0.15
    ents
    -0.15
    RIES
    -0.14
    ogui
    -0.14
    enda
    -0.13
    lendirme
    -0.13
    rend
    -0.13
    etur
    -0.12
    POSITIVE LOGITS
     whenever
    0.32
     when
    0.32
     situations
    0.29
    when
    0.26
     cuando
    0.24
     quando
    0.24
     khi
    0.24
     if
    0.23
    	when
    0.23
     nếu
    0.22
    Act Density 0.198%

    No Known Activations