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

    Neuronpedia

    INDEX
    Explanations

    terms related to hobbies and leisure activities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     DeV
    -0.67
    Vist
    -0.61
    WriteLiteral
    -0.60
    ModelAttribute
    -0.60
     condamné
    -0.58
    tnt
    -0.58
     muka
    -0.58
    hline
    -0.57
     win
    -0.57
     présent
    -0.57
    POSITIVE LOGITS
     Hobby
    1.11
    Hobby
    1.06
     pleaſure
    1.05
     hobby
    1.04
    leisure
    1.02
     leisure
    1.00
     Leisure
    1.00
    hobby
    1.00
    Leisure
    0.98
     hobbies
    0.95
    Act Density 0.022%

    No Known Activations