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

    Neuronpedia

    INDEX
    Explanations

    references to website functionality and user experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aji
    -0.16
    _sensitive
    -0.15
    rup
    -0.15
    tera
    -0.15
    cks
    -0.14
     Spears
    -0.14
    çĻº
    -0.14
    γγ
    -0.14
    VOKE
    -0.14
    cko
    -0.13
    POSITIVE LOGITS
     anonymous
    0.19
    anonymous
    0.19
    Anonymous
    0.19
     anonymously
    0.19
     Anonymous
    0.18
     usage
    0.17
    åĮ
    0.17
     anonym
    0.17
     patterns
    0.17
    anon
    0.16
    Act Density 0.011%

    No Known Activations