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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to actions, particularly in a context involving preparation and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    úa
    -0.17
    ición
    -0.17
    ución
    -0.17
    ación
    -0.17
    aban
    -0.16
    ulario
    -0.16
    .scalablytyped
    -0.16
    amientos
    -0.16
    aba
    -0.15
    ización
    -0.15
    POSITIVE LOGITS
    aram
    0.27
    ou
    0.27
    rou
    0.22
    ARAM
    0.21
    ava
    0.20
    iou
    0.20
     ou
    0.19
    avel
    0.19
    OU
    0.18
    asse
    0.18
    Act Density 0.011%

    No Known Activations