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

    Neuronpedia

    INDEX
    Explanations

    phrases that express positive evaluations or praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bes
    -0.17
    onto
    -0.15
    undry
    -0.15
    iams
    -0.14
    assage
    -0.14
    omo
    -0.14
     tá»Ń
    -0.14
    un
    -0.14
    ©
    -0.13
    ogui
    -0.13
    POSITIVE LOGITS
     enough
    0.24
    ä¸Ķ
    0.21
     Enough
    0.17
    stvo
    0.15
     chance
    0.15
    storybook
    0.15
    reetings
    0.15
    ÑĤÑĮ
    0.14
    ;y
    0.14
    ิà¸Ļà¸Ķ
    0.14
    Act Density 0.239%

    No Known Activations