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

    Neuronpedia

    INDEX
    Explanations

    references to influence or impact in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruba
    -0.17
     Blasio
    -0.17
    nem
    -0.17
    isser
    -0.15
    ambre
    -0.15
    ãģ¹ãģį
    -0.15
    ãĤ¦ãĤ©
    -0.15
    ish
    -0.15
    à¸ģ
    -0.15
    achten
    -0.15
    POSITIVE LOGITS
    oft
    0.18
    uated
    0.16
    ìĤ¬íķŃ
    0.15
    amac
    0.15
    627
    0.15
    ential
    0.15
    ively
    0.15
    847
    0.15
    std
    0.14
     sons
    0.14
    Act Density 0.029%

    No Known Activations