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

    Neuronpedia

    INDEX
    Explanations

    references to friendship and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.60
     Thirdly
    -0.51
     mellitus
    -0.48
     gereken
    -0.48
     Walkover
    -0.47
    êtements
    -0.46
    ÓG
    -0.45
     ansi
    -0.45
    üller
    -0.45
    roja
    -0.45
    POSITIVE LOGITS
    hips
    0.90
    SHIP
    0.85
    ſhip
    0.81
    liest
    0.79
     детства
    0.77
    zoned
    0.77
    lies
    0.75
    consulté
    0.72
    ship
    0.72
     circle
    0.70
    Act Density 0.122%

    No Known Activations