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

    Neuronpedia

    INDEX
    Explanations

    government-related terms and budgetary references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilia
    -0.15
    ador
    -0.15
    acic
    -0.15
    anger
    -0.14
    ABI
    -0.14
    .Accessible
    -0.14
     Alonso
    -0.13
    aden
    -0.13
    _abort
    -0.13
    acion
    -0.13
    POSITIVE LOGITS
    Âłb
    0.22
     BOTTOM
    0.19
    ÂłB
    0.18
     b
    0.18
    ,b
    0.17
     BRAND
    0.17
    ¬¬
    0.17
    ,B
    0.17
     BN
    0.17
     BO
    0.17
    Act Density 0.070%

    No Known Activations