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

    Neuronpedia

    INDEX
    Explanations

    words that convey positivity and appreciation for experiences or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otic
    -0.15
    áp
    -0.15
    ein
    -0.15
    -0.15
    angelo
    -0.15
    ä¼į
    -0.15
    unga
    -0.14
    иÑĢов
    -0.14
    .ll
    -0.14
     bá»ı
    -0.14
    POSITIVE LOGITS
    ness
    0.17
    lest
    0.17
    oins
    0.16
    ously
    0.15
    ipple
    0.15
    indsight
    0.15
    kova
    0.14
    oes
    0.14
    rum
    0.14
    mente
    0.14
    Act Density 0.012%

    No Known Activations