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

    Neuronpedia

    INDEX
    Explanations

    questions related to experiences, preferences, or highlights in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iente
    -0.18
    ellite
    -0.16
    оÑĤоÑĢ
    -0.15
    lant
    -0.14
     Chill
    -0.14
    umi
    -0.14
    ano
    -0.14
    stras
    -0.13
    家
    -0.13
    arget
    -0.13
    POSITIVE LOGITS
    CADE
    0.16
     Milf
    0.14
    便
    0.13
     vod
    0.13
    (..
    0.13
    .DO
    0.13
     Vance
    0.13
    axis
    0.12
    InputChange
    0.12
     Ùĩد
    0.12
    Act Density 0.049%

    No Known Activations