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

    Neuronpedia

    INDEX
    Explanations

    references to delicacies and expressions of appreciation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation and descriptions of delicacies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rothschild
    -0.73
     Wall
    -0.72
     Primordial
    -0.70
     Mage
    -0.69
     Fields
    -0.68
     Trip
    -0.66
     Hole
    -0.66
     fingerprints
    -0.65
     Steps
    -0.65
     calculus
    -0.65
    POSITIVE LOGITS
    ately
    1.29
    uously
    1.15
    ably
    1.15
    acies
    1.07
    atures
    1.03
    ality
    1.00
    ators
    0.97
    itives
    0.97
    acy
    0.97
    atively
    0.96
    Act Density 0.026%

    No Known Activations