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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various forms, surprises, costs, and characteristics of different items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AFX
    -0.14
    alara
    -0.14
    quia
    -0.14
    resher
    -0.14
    -controls
    -0.14
    ognito
    -0.14
    iedad
    -0.14
    olvers
    -0.14
    rimp
    -0.14
    ilst
    -0.14
    POSITIVE LOGITS
    leigh
    0.16
     bracket
    0.14
     Hob
    0.14
     sit
    0.14
     qu
    0.13
     consultation
    0.13
    .scenes
    0.13
    ponible
    0.13
    way
    0.13
    flower
    0.13
    Act Density 0.181%

    No Known Activations