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

    Neuronpedia

    INDEX
    Explanations

    mentions of social security and welfare systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _allocator
    -0.16
    ocha
    -0.15
    ãĥ«ãĤ¯
    -0.15
    angi
    -0.15
    Esc
    -0.15
     Esc
    -0.15
    ewan
    -0.15
    915
    -0.14
    ampa
    -0.14
    าà¸ĺ
    -0.14
    POSITIVE LOGITS
     contrib
    0.29
     pension
    0.25
     sickness
    0.23
    -contrib
    0.22
     social
    0.22
     Contrib
    0.22
     Lump
    0.22
     pensions
    0.21
     Pension
    0.21
    Contrib
    0.21
    Act Density 0.048%

    No Known Activations