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

    Neuronpedia

    INDEX
    Explanations

    references to a person's interests and hobbies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    personal interests and occupations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     effec
    -0.49
    iettivo
    -0.47
    rrggbb
    -0.46
     برانيه
    -0.45
    GRANTED
    -0.44
     effek
    -0.43
    Przypisy
    -0.43
     мәкал
    -0.43
     Mathews
    -0.41
     noDo
    -0.40
    POSITIVE LOGITS
     avoient
    0.52
    StructEnd
    0.43
     auroit
    0.43
     hobbies
    0.42
    TemporalType
    0.41
     fubject
    0.41
     lifestyle
    0.41
     élet
    0.41
    Hobbies
    0.40
    webElementXpaths
    0.40
    Act Density 0.025%

    No Known Activations