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

    Neuronpedia

    INDEX
    Explanations

    references to citations or annotations in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orra
    -0.15
    deaux
    -0.15
    +-+-+-+-+-+-+-+-
    -0.15
    /tos
    -0.14
    TypeInfo
    -0.14
    PasswordEncoder
    -0.14
    annes
    -0.14
    seo
    -0.13
    CHANT
    -0.13
    proto
    -0.13
    POSITIVE LOGITS
    roller
    0.15
    a
    0.15
    yer
    0.15
    rollers
    0.15
     Shane
    0.14
    igel
    0.14
    adin
    0.14
    imed
    0.14
    ycop
    0.14
    Ùħد
    0.14
    Act Density 0.041%

    No Known Activations