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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional or subjective expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Affero
    -0.16
    rawler
    -0.15
    ogan
    -0.15
    plusplus
    -0.14
    ylie
    -0.14
    žil
    -0.14
    à¸ŀร
    -0.14
    à¹Ģà¸Ĥà¸ķ
    -0.14
    ÏĥÏĦά
    -0.14
    žel
    -0.14
    POSITIVE LOGITS
    idor
    0.16
     Tib
    0.16
     sensor
    0.15
     quality
    0.15
    üre
    0.14
     typical
    0.14
    èĪ
    0.14
     bare
    0.14
     sf
    0.14
    aison
    0.14
    Act Density 0.006%

    No Known Activations