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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ties or connections, both literal and metaphorical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endency
    -0.16
    озÑı
    -0.15
    endencies
    -0.15
    ëŁ¼
    -0.15
    colo
    -0.15
    ansi
    -0.15
    iers
    -0.14
    ivate
    -0.14
    -Sah
    -0.14
    erne
    -0.14
    POSITIVE LOGITS
     Knot
    0.19
    backs
    0.18
    /dis
    0.16
    hold
    0.16
    lessly
    0.15
    lfw
    0.15
     knots
    0.15
    urious
    0.15
     Lug
    0.15
    holder
    0.15
    Act Density 0.060%

    No Known Activations