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

    Neuronpedia

    INDEX
    Explanations

    the presence of discussions about influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Aub
    -0.71
    {*
    -0.69
     mères
    -0.68
     Peralta
    -0.67
     perfección
    -0.67
     Zeller
    -0.66
     anteriore
    -0.66
    Alfredo
    -0.64
    artem
    -0.64
     dalamnya
    -0.64
    POSITIVE LOGITS
     influence
    2.66
     Influence
    2.53
    influence
    2.49
    Influence
    2.48
     influences
    2.45
     INFLUENCE
    2.31
     Influences
    2.29
     influencing
    2.17
     influenced
    2.08
    Influ
    2.08
    Act Density 0.113%

    No Known Activations