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

    Neuronpedia

    INDEX
    Explanations

    expressions of significant negative experiences or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.16
    uner
    -0.16
    dera
    -0.16
    gii
    -0.15
    Ïģε
    -0.15
    istra
    -0.14
    ีà¸ļ
    -0.13
    enting
    -0.13
    athlon
    -0.13
    aoke
    -0.13
    POSITIVE LOGITS
     Affero
    0.15
    brace
    0.14
     domic
    0.14
    .Abstractions
    0.14
    rios
    0.13
    ίοÏĤ
    0.13
    AINED
    0.13
    ">//
    0.13
    359
    0.13
    .heroku
    0.13
    Act Density 0.747%

    No Known Activations