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

    Neuronpedia

    INDEX
    Explanations

    phrases that express generalizations or summaries of experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¸ķà¸Ļ
    -0.15
    insky
    -0.14
     wedge
    -0.14
    ruh
    -0.14
    bond
    -0.14
    öm
    -0.14
    onium
    -0.14
    hta
    -0.14
    addon
    -0.14
    öh
    -0.13
    POSITIVE LOGITS
    AVA
    0.16
    üstü
    0.15
     Twig
    0.15
    emailer
    0.15
     newPassword
    0.15
    alker
    0.14
    elden
    0.14
    ignon
    0.14
    aley
    0.14
     dequeueReusableCellWithIdentifier
    0.14
    Act Density 0.013%

    No Known Activations