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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal interests and hobbies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.58
     ModelExpression
    -0.51
    ']))
    -0.49
    }}],
    -0.47
     الرئيسي
    -0.45
    tedra
    -0.45
    MENAFN
    -0.44
    APORE
    -0.44
     गरे
    -0.43
     trå
    -0.42
    POSITIVE LOGITS
     hobbies
    0.90
     Hobbies
    0.75
     enjoys
    0.72
     contextLoads
    0.71
     loves
    0.67
    WebVitals
    0.66
     pleaſure
    0.64
    Hobbies
    0.63
     enjoying
    0.60
     chofe
    0.60
    Act Density 0.089%

    No Known Activations