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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote construction, development, and relationship-building efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyse
    -0.18
    loi
    -0.16
    iras
    -0.16
    heits
    -0.15
    .sb
    -0.15
     directions
    -0.15
    çĢ¬
    -0.14
     Kaw
    -0.14
     Harden
    -0.14
    éri
    -0.14
    POSITIVE LOGITS
     rapport
    0.19
     reputation
    0.18
     relationships
    0.17
    .build
    0.17
     Reputation
    0.17
     groundwork
    0.16
    (build
    0.15
     capacities
    0.15
     capacity
    0.15
     relationship
    0.15
    Act Density 0.091%

    No Known Activations