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

    Neuronpedia

    INDEX
    Explanations

    references to friendships and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ors
    -0.19
    itz
    -0.18
    erse
    -0.17
    utsch
    -0.16
    ions
    -0.15
    ãĤ¤ãĤ¯
    -0.15
    NotificationCenter
    -0.15
    union
    -0.15
    ordon
    -0.15
    orsch
    -0.14
    POSITIVE LOGITS
    liness
    0.30
    ships
    0.25
    lier
    0.24
     WithEvents
    0.21
    liest
    0.21
    lies
    0.19
    SHIP
    0.19
    ship
    0.19
    chaft
    0.17
    Ship
    0.16
    Act Density 0.034%

    No Known Activations