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

    Neuronpedia

    INDEX
    Explanations

    references to personal hobbies and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azo
    -0.17
    ÑİÑĢ
    -0.15
    urr
    -0.15
    IJëĭ¤
    -0.14
    esto
    -0.14
    ovsky
    -0.14
    jev
    -0.13
    zap
    -0.13
     ä¸
    -0.13
    Ỽp
    -0.13
    POSITIVE LOGITS
     hobby
    0.52
     hobbies
    0.51
     Hobby
    0.42
     passions
    0.41
     passion
    0.41
     interests
    0.41
     past
    0.39
     activities
    0.37
    obbies
    0.36
     activity
    0.35
    Act Density 0.309%

    No Known Activations