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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of influence or being influenced

    oai_token-act-pair · gpt-3.5-turbo

    the concept of influence or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.70
    VK
    -0.70
    çĦ
    -0.67
    ENA
    -0.65
    clamation
    -0.64
    fal
    -0.64
    Sham
    -0.64
    á
    -0.64
    cake
    -0.64
    FT
    -0.64
    POSITIVE LOGITS
     influenced
    1.21
     adversely
    0.92
     influences
    0.89
     swayed
    0.88
     influencing
    0.88
     negatively
    0.87
     confir
    0.85
     favorably
    0.83
     materially
    0.82
    awaru
    0.81
    Act Density 0.034%

    No Known Activations